0% found this document useful (0 votes)
212 views98 pages

Research Lecture One

The document provides lecture notes on research methods. It discusses the importance of research, types of research including basic, applied and evaluation research. It also covers topics like the significance of research, qualities of a good researcher and problems faced by researchers.

Uploaded by

Namukasa Divina
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
212 views98 pages

Research Lecture One

The document provides lecture notes on research methods. It discusses the importance of research, types of research including basic, applied and evaluation research. It also covers topics like the significance of research, qualities of a good researcher and problems faced by researchers.

Uploaded by

Namukasa Divina
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 98

FACULTY OF ENGINEERING

Department of Civil and Building Engineering

RESEARCH METHODS MODULE

LECTURE NOTES
YEAR II, SEMESTER II

BY: JAMES KAZUNGU .A (Eng)


MS GLO in Prog, PGD(PPM), B.ENG, DIP IN CIVIL
&BUILDING
[email protected]
0772670685

Academic year 2018/2019

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 0 of 98
1.0) INTRODUCTION TO RESEARCH METHOD MODULE

The objective of this module of research methods is to introduce students to the basic
concepts and tools of research and to enable them to acquire skills of conducting
research and arrive at meaningful conclusions, several people have conducted
research but at the end of the research period they fail to achieve to intended
purposes for which the research was done, this is due to many reasons and failure to
adhere to the principles and ethics of research, details of this will be discussed in the
chapter ahead.

Class Activity (1): write and explain several reasons as to why a research may fail to
address its intended purpose or objective in your community or at the work place.

There is a critical reflection: Research is to see what everybody else has seen and think
what nobody else has thought, Albert Szent-Gyorgyi.

Schaumacher (1997) Defines research as being a systematic process of collecting and


analyzing data for some purpose, such a purpose he observes may be to solve a
problem, to generate or expand knowledge, or just for evaluation.

According to Kothari (2003), Research is the Art of scientific investigation; Kothari


proceeds to define research as the systematic, controlled, empirical and critical
investigation of the relationship among natural phenomena intended to produce
verifiable and generalizable knowledge.

Research is not about information gathering (Gathering information from sources such
as books, journals etc, Transportation of facts (No contribution of new knowledge).

1.1) RESEARCH AS A SCIENTIFIC APPROACH

Scientific method is a systematic and controlled process of collecting empirical data


relating to a phenomenon, and scientifically analyzing data to develop inferences or
conclusions about the issues at hand, to test hypothesis, or answer pertinent questions,
scientific process is so far the best approach to establishing the truth about most
phenomenon, it combines the characteristics of inductive and deductive reasoning,
it has time tested well established procedure that must be followed to avoid bias. The
results of scientific study can be verified by other researchers to confirm the
results/findings.

The fact that it can be repeated on several times by different researchers and
producing the same results or to be within the accepted limits makes it valid and
reliable, therefore research is valid as scientific because:
RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 1 of 98
1). it involves search for knowledge (something new about something),

2). Systematic (Follows procedures/plans and designs),

3). Empirical (Evidence based and truth about information you have either positive nor
Negative outcome),

4). carefully designed (Not Speculative, based on a clear problem new data answers,
original research questions) and finally

5). Objective (can be interpreted and verified and is free from bias).

Class Activity (2) Write down detailed explanations on why Hallmarks value research
as being scientific approach rather than any other approach.

1.2) THE SIGNIFICANCE OF RESEARCH IN THE WORLD TODAY

The world has changed and will continue changing, this changes are attributed to the
efforts of research to add knowledge or fill the missing gaps of what is already existing.

1). Research avails the relevant information that acts as a basis for i.e. policy
formulation, Evaluation, designing, improvement of the current modal, manufacturing
of new products and Development of New theories and laws etc.

2). Source of Power through information, Research gives us broad view on events,
things, processes and people, it enlightens and opens us to new horizons, and it breaks
the tendency of group-think and protection of status quo. It makes life better and
forces to develop new attitudes, values, interest, frames of reference and viewpoints
to issues

3). Solving Complex Issues, it reduces dependence on institution in decision making, it


allows or assists officials to approach problems systematically or scientifically, to dig out
the facts which intuition and experience alone could not discover, it further avoids try
and error approach to errors which may lead to a wrong relationship between
variables.

4). Proven and reliable information, Research intends to acquire information that is
complete, accurate, update, cost effective verifiable, relevant and timely to serve the
intended purpose or solve the problem at hand, through comprehensive research the
risk of the unknown-unknown is managed.

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 2 of 98
5). Practicality of existing theories, some researchers venture into research to examine
the practicality of existing theories and how to apply them best or refine them and
others undertake them to verify findings of other researchers, the aim is to prove or
disapprove the findings. Etc

6). Deals with problems, attitudes and Opinions

7). Attempts to seek answers to questions

8). Draw conclusions from data

9). Aid in forecasting and planning.

10). Etc

ASSIGNMENT NUMBER ONE:

Research in the world today has changed a number of Polices, Decisions and major
structural changes both in the Government and public sector including much more
innovations, all aimed at the betterment of facilities and services in the world, these
researchers to produce good results ought to bear some qualities, on the other hand
they also face several problems in the course of fact finding mission.

a) Explain the qualities of a good researcher (10 marks)

b) With example explain in details problems faced by researchers in the course of


executing their duties. (10 Marks)

2). Types of Research

Research is basically categorized according to:

1) The purpose it serves in real life or its application (Applied research)

2) The type of data collected (Qualitative and quantitative Research)

3) Nature of the research Design(Experimental or Non experimental)

4) Question answered (Explanatory or why question) or exploratory (what question)

5) Purpose of the research (Basic /Pure research)

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 3 of 98
1).Basic Research

Basic research is also known as fundamental or pure research, this type of research is
not meant for a specific application, its general research meant to explore unknown
phenomenon for the sake of enhancing a researcher’s knowledge. Its conducted with
no particular aim of solving an immediate problem in real life but rather conducted on
a curiosity basis of a particular researcher. Although it may not have a practical
implication to society at a particular time, it may be of importance in future. It’s
however important to note that most important discoveries have been realized
through basic research and on the other hand it’s the basis for applied research.

Basic Research has under it the following: Action Research, Evaluation Research and
Social Impact assessment.

2).Applied Research:
This is the research that is goal oriented, meant to address specific problem in real life
or to solve a particular problem in the society, it focuses on a particular or specific
problem area, or application. It aims at enhancing or redefining knowledge through
basic research- with a view of applying it in real life situation, examples include:
Marketing research, production Research, medical Research. Etc in a nutshell it
focuses on a problem and must have an objective of solving the problem.

Applied research has under it the following: Causal-Comparative research, Descriptive


research and explanatory research.

3) Evaluation Search
Research is done to evaluate the impact of an intervention, it involves determining the
worth of or the extent to which goals have been attained. It may sometimes be called
an impact research, assessment research or social accountability research.

In summary the categorization of research is done depending on the

a) The nature of the problem to be investigated

b) The goal or aim of the research

c) The use of the theory

d) The techniques to be used. For details please Read Amin(2005) page 16-22
RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 4 of 98
2.1). THE SIGNIFICANCE/IMPORTANCE OF RESEARCH, (KOTHARI 2003)

1) We research to gain familiarity with the phenomenon.

2) To portray accurately the characteristics of a particular individual, situation or


group.

3) To determine the frequency with which something occurs e.g.…….

4) To test a hypothesis of a causal relationship between variables

5) To desire to get a research degree like in your situation or case.

6) The desire to face challenge of solving a pending or unsolved problem in a


community or society.

7) The move or desire to get an intellectual joy or Hon. In doing something creative or
something that adds value to the betterment of life.

8) The desire to be of service to the society and finally

9) The desire to get respect within the Public for a remarkable input that can always
be referred to by generation and generation.

2.2 CHARACTERISTICS OF A GOOD RESEARCH

Disciplinary Embedding
Research is broad in its nature, therefore the theme and topic must be clear and
showing clearly the discipline that you are contributing towards.

Relevance
The key question is that: is the research that am undertaking leading to new
information/ current/ topical, what is the usefulness of what am carrying out? Is the
statement information enough (scope) of your research to bring positive changes in
the society? Would this study substantially revise or extend existing knowledge or lead
to something useful in the best practice.

Precision
Are the units of analysis clear and the subject? How large is the population affected,
and how important is it, is it influential, or how popular is the population? And finally
what are the key variables and dimensions.
RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 5 of 98
Functionality
What is the type of the research that you are undertaking? Is it basic research or
applied research and the main question after knowing the type is that does the
structure of the problem or study design reflect its function?

Consistency
This is the discipline of the research, the reason and strategy logically laid out?

Questions like is there evidence or authoritative option from others to support the need
for this research is always very paramount.

Verification
The research subject must be opened to verification by others so that if it’s proven right
and on principles it can be challenged.

Empirical Evidence
The research must be backed up by evidence, this will assist in statistical presentation
and writing of the problem statement, where need be the evidences must be
attached in the final proposal or report as appendix material.

Research is Systematic
In reference to our earlier discussion where we agreed and found out fact as to why
research is scientific in nature, this implies that it has a certain partner or direction or
structure and is carried out following specific rules, steps and procedures, which when
then followed under a controlled environment must then lead you to a meaningful
conclusion.

Research is Logical
The implication of research being logical means the researcher ought to think beyond
the box and employs logic or systematic reasoning at the conceptual stage,
development and final reporting to ensure that true outcome of the process or
research is seen to solve the problem at hand.

Research is Reductive in Nature


This means that when a researcher applies analytical procedures to collect data, the
confusion of individual events and objects are reduced to more understandable
categories and concepts.

Research is Transmittable
This means that the result of a given study can be employed in understanding or
solving problems outside that specific context of study especially for similar conditions

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 6 of 98
and nature of the problem, if possible minor adjustments may be employed to suit the
environment where it will be implemented.

Research is Replicable
The study on a particular subject may be repeated if deemed important.

Research is Cyclical
This means it does not end with the findings of a solution to the identified problem.

2.3 The Research Process

• Problem identification
• Research objectives/questions/hypothesis that further clarify the research
problem

• Review of related literature


• Methodology (research designs, population, sample, data collection.
• Data collection
• Data analysis (presentation, Analysis and interpretation)

• Writing report/Dissemination.

2.5 APPROACHES TO RESEARCH

Research can either be quantitative or qualitative

Quantitative Research

This type of research that describes the phenomena in numbers and measures instead
of using words, quantitative research relies on the principles of verifiability i.e.
Knowledge emerges from what can be proven by direct observation.

Quantitative approaches are applicable when, Data is expressed in numbers, data is


analyzed using statistical methods, frequencies are sought to explain meanings of
presentations made, generalization is needed in order to chive representativeness.
There is need to control as many variables as possible.

Quantitative research is positivism in approach, key elements of positivism include.

An objective truth exits, truth is revealed through use of scientific methods, researcher
is independent from what is researched etc.
RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 7 of 98
Steps in quantitative research process

1) Preparation

2) Selection of the research problem

3) Data collection

4) Data processing

5) Reporting

Qualitative Research

This the type of research where the phenomena are described in words instead of
numbers, it seeks to describe and analyze behavior from the point of view of those
being studied.

Its purpose is majorly to promote greater understanding of the phenomena and the
methods of data collections are: Extensive observations, interviews and focus group
discussions.

2.6 APPLICATION OF QUALITATIVE APPROACH OF RESEARCH.

1) It’s used where the subject matter is unfamiliar

2) Dealing with hard to research respondents

3) The researchers seeking for meanings rather than frequencies

4) Where there is need for an in-depth analysis

5) Where flexibility is needed to allow for discovery of unexpected information etc.

Assignment no.2 Compare and contrast the qualitative and quantitative approaches
to research. (Illustration with a table may be used if applicable)

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 8 of 98
2.7 TRIANGULATION APPROACH TO RESEARCH

This is another research approach that tries to combine the weakness of both the
qualitative and quantitative approaches.

-This approach attempts to integrate both the qualitative and quantitative methods

-Inadequacies of each method is minimized

-more valid and reliable outcomes are obtained

-it conforms that data generated is not due to chance or circumstances etc.

3.0) RESEARCH VARIABLES, OBJECTIVES, QUESTIONS, HYPOTHESES AND CONCEPTUAL


FRAMEWORK

3.1 Variable:
-A characteristic that takes on different values/conditions for different individuals.

-its anything that varies/takes on more than one form.

Variables should have two distinct characteristics that is: Should me mutually exclusive
and should be exhaustive. Variables should have dimensions and dimensions must
have indicators e.g. sex, Employment, reward management, marital status etc.

3.2 Variable and Research


Research is the study of the relationship between variables, therefore there must be at
least two variables in a research if not then there is no relationship to study.

The main variables are the dependent variables and independent variables that must
be clearly stated always in the topic/ title of research and in the statement of the
problem.

3.3 Types of Variables in Research


We shall consider the variables below in our research method module

1) Independent variable,

2) Dependent Variable

3) Moderator variable

4) Intervening variable

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 9 of 98
1). Independent variable

This is the variable that affects the dependent variables under study and is included in
the research design so that its effects can be determined, it’s also known as predictor
variable in certain types of research.

They help to explain/account of variation in the dependent variables.

2). Dependent Variable


This is the variable being affected or assumed to be affected by the independent
variable and does not include all the specific information.

The dependent variable is the variable of interest; it’s the one that causes the research
to be inquisitive enough to carry out research

It’s the variable that is used to measure the effects of the independent variables, its
also known as an outcome research in certain types of research.

3). Moderator Variable


This is a variable that may or may not be controlled but has an effect on the research
situation. When controlled- control variable (effects are known), when uncontrolled-
intervening variables (effects are unknown)

This variable help to moderate the relationship between the independent and
dependent variables.

4). Intervening Variables

A variable whose existence is inferred but which cannot be manipulated or directly


measured, it’s also known as Nuisance Variables, mediator variable or confounding
variables. This variable may interfere with the experiment if not taken into account or
consideration. E.g. attitude of workers can be an intervening variable in the above
example.

3.4 RESEARCH OBJECTIVES

What are research objectives?

• These are fine statements that show what is to be achieved by the study.

• Suter 2006, says Research objectives comprehensively describe what the


researcher wants to focus on, do and achieve at the end of the study.

RESEARCH METHODS LECTURE NOTES FOR YEAR II: BY JAMES KAZUNGU ALUKO (ENG),
Masters in Geology in prog, PGD in project Planning and Management, Bachelor’s Degree in Civil and
Building and Diploma in Civil and Building Engineering Email:[email protected]. 0772 670685
Page 10 of 98
• Research objectives conceptualizes the relationship between variables which
define parameters of the problem

3.5 The Importance of the Objectives

1) They determine the variables that will be identified in the conceptual and
theoretical framework.

2) They assist the researcher to formulate testable hypotheses.

3) They also guide the researcher in formulating research questions.

In summary objective assist in

a) Focusing the study (narrowing it down to the essentials

b).Avoid the collection of data which are not strictly necessary for understanding and
solving the problem that the researcher has identified.

c) Organize the study in clearly defined phases.

3.6 Types of Objectives

We shall look at the two basic types of objectives namely:

1) General objectives/Purpose

2) Specific objectives /Objectives

1) Purpose of the study/ General Objectives

The student should make a choice to either use purpose of the study or general
objective of the study but not both. A study should be based on the clear
conceptualization of the relationship between variables, which defines the parameters
of the problem of the study.

The objective or purpose of the study spells out how the postulated relationship will be
investigated and what the research intents or hopes to achieve by carrying out
proposed study.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 11 of 98
The General objectives should indicate the intent of the study and should reflect or
show the independent and the dependent variables of the study including other
variables that are deemed important to the study.

2). Specific objectives or objective of the study

Specific objectives arise directly from the general objective of the study, in case a
study has used ‘purpose’ of the study in (1) above, this section should be called
objectives of the study however where general objective is used then the this section
adapts specific objectives.

It’s further important to note that the number of specific objectives is therefore
influenced by the conceptualization and the nature of the relationship the researcher
may be interested in investigating. The number of specific objectives will influence the
volume of literature review and data to be collected and hence the volume of the
report.

Class example.

Considering an example of Management of Kyambogo University Engineering faculty


and performance of the students. The word management can be conceptualized into:

❖ Planning

❖ Organization

❖ Leadership

❖ Staffing

We can generate the objectives from this topic as follows:

1).To investigate the role played by planning on performance of students at faculty of


Engineering of Kyambogo University.

2).To establish the relationship between the organization structure and performance of
students at faculty of Engineering of KYU.

3). To examine the effect of leadership within the faculty of engineering in relation to
the performance of the students.

4). To explore the effect of staffing on the performance of the students at the faculty
of civil and building Engineering of KYU.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 12 of 98
The following words can be used in expressing the objective of the study: to determine,
to compare, to investigate, to explore, to find out, to establish, to inquire and to
examine but not the following(biased words: to show, to prove, to confirm, to verify, to
see, to indicate, to illustrate, to check etc.

In conclusion, objectives should be SMART

• Stated in specific and Measurable attribute.

• Achievable within a given timeframe and cost.

• Authentic to portray the exact situation on ground

• Relevant to particular Study/research

• Time bound

4.0) RESEARCH HYPOTHESES

An hypothesis is a statement of the researcher’s prediction or guess of the relation that


exists among the variables being investigated, in other words it’s the tentative answers
to the research problem pending verification of which verification is through the
research that will either prove it right or wrong, please note its unethical for a
researcher to force his/her hypothesis wrong if the research says the hypothesis is not
correct please accept the outcome rather than compromising the research of the
research by accepting what the research has disagreed with, this process in research
will lead us to type one error and type two errors which will be discussed in future. It’s
further important to note that the variables that in the objectives should appear in the
hypothesis.

For the case of quantitative research hypotheses are stated before collecting data
whereas in qualitative research hypotheses are often generated as data is being
collected and as the researcher gains insight into the prevailing subject of the
research.

4.1) Types of Hypotheses

Null Hypotheses, The hypothesis that is actually tested is referred to as null Hypothesis
and is symbolized as (HO) and the second type being the Alternative Hypothesis (H1)
which at times is also referred to as research Hypothesis.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 13 of 98
Usually although not always, the null hypothesis states that there is no difference
between several groups or no relationship between variables, whereas the research
hypothesis may predict either positive or negative relationship.

A null hypothesis states that no relationship exist between the variables of interest; and
a declarative hypothesis (experimental hypothesis gives a positive statement about
the outcome.

A hypothesis could also be referred to as simple or complex in nature, a simple


hypothesis consists of only two variables whereas a complex hypothesis consist of two
or more variables.

A simple hypothesis could be of associative or of casual nature, the associative


hypothesis tests a relationship between two variables that have casual effect on each
other. A casual hypothesis presupposes a causal relationship between two or more
variables, it could also be null or declarative hypothesis.

A working hypothesis is provisionally accepted when no alternatives are available- like


all hypotheses, a working hypothesis can be constructed as a statement of
expectations. They can be linked to the exploratory research purpose in the empirical
investigations and is further often used as conceptual framework as they are well
suited to qualitative research methods. etc.

5.0) RESEARCH QUESTIONS

A Research question ask about the relationship between two or more variables of the
study, it’s important to note that research questions are directly derived from the
objectives of the study.

Research questions focus or narrows down the study to the essentials and avoids
collection of data that are not necessary to the study relationship.

5.1) RELATIONSHIP BETWEEN RESEARCH OBJECTIVES, QUESTIONS AND HYPOTHESES

• The relationship between research objectives, questions and hypotheses can be


concluded from the fact that all the three have the same variables.

• Research questions are directly derived from the objectives.

• Tentative answers to research questions are provided by the hypotheses

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 14 of 98
5.2) THEORY IN RESEARCH

A theory is a set of systematically tested and logically interpreted prepositions that


have been developed through research that explains social phenomena.

Theories help a researcher to explain, describe, understand or even predict some


phenomena in a systematic manner.

A theory provides the basis for establishing the hypotheses to be tested in the study, a
good theory is can logically be broken down into a set of hypotheses which can be
tested/verified through experiments or observations.

5.3) THE CONCEPTUAL FRAMEWORK

The conceptual framework is a scheme of concept (or variables) which the


researchers operationalize in order to achieve set objectives; it’s a diagrammatic
representation of the variables.

The concepts are presented as a model where research variables and the relationship
between them are translated into visual picture to illustrate the interconnections
between the independent, extraneous and dependent variables.

Conceptual framework showing the relationship between the variables

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 15 of 98
Rewards (independent variable) Performance: (Dependent)
Monetary Rewards Performance
-Basic salary
-Timeliness
-Allowances
-Overtime payment -Customer Care

Non-Monetary -Quality of Work


Rewards
-Recognition
-Career Development
-Training

Moderating variable
Polices
Employment policy
Retirement Policy

5.4 THE ADAVANTAGES AND DISADVANTAGES OF A CONCEPTUAL FRAMEWORK

The advantages include but not limited to:

• It helps to understand the research project in details through operationalization


and itemization

• The framework explains the research ideals and relationship between the
variables under study.

• Guides on the research process through objectivity of the subject at hand.

• Provides the conceptual and the methodological tools for formulating the
hypotheses and theories. Etc.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 16 of 98
The Disadvantages

• The conceptual framework may over simplify the problem

• It may not be well suited to the application

Group Class Room Task One.

Consider a topic/theme of “The status of road infrastructures and the percentage of


road accidents in Uganda”, a case of Kampala-Mbarara Highway.

From the topic above

Generate the objective of the study

Specific objectives of the study

Research questions and hypothesis

Draw the conceptual framework indicating the independent, dependent,


moderating variables including intervening variables.

Topic two

The lecturing strategies used at Kyambogo University and the performance of Students
in the field, A case of Faculty of Engineering.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 17 of 98
5.5) APPROACHES FOR DERIVING THE OBJECTIVES OF THE RESEARCH STUDY

• Dissecting the research purpose into component parts to make research


objectives.

• This can be done on the basis of many to one model and linking the elements of
the model to the variables, one to many model and many to many.

Many to one Approach

This is done by deriving the objectives by dissecting the independent Variables (IV)
IV1 IV2 IV3

DV

One to many model

IV

DV1 DV2 DV3

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 18 of 98
Many to many model

5.6) How state research objectives must be stated

To investigate…………………………………………..

To ascertain …………………………………………….

To find out……………………………………………….

To verify………………………………………………….

To explore……………………………………………….

To establish……………………………………………..

To assess………………………………………………..

To examine…………………………………………….

5.7).SOME APPLICABLE EXAMPLES ON CONSTRUCTING RESEARCH OBJECTIVES

1. To explore how staff welfare affects performance of Uganda Police in Lira district
of northern Uganda.

2. To establish the relationship between academic qualification level and


obtaining of a higher profile Job.

3. To examine how judicial reforms affects service delivery in the judiciary sector.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 19 of 98
4. To assess the contribution of the current number of members of parliament in
relation to government performance in all sectors of the economy.

5. 8). RESEARCH QUESTIONS EMERGING FROM THE ABOVE RESEARCH OBJECTIVES.

1. What is the relationship between the Uganda Police welfare and performance
in Lira district of Northern Uganda?

2. How does the academic qualification level affect one’s obtaining of higher
profile job?

3. How is judicial reform affecting the service Delivery in the judiciary sector?

4. Is there contribution of the current numbers of members of parliament in line with


government performance in all sectors in the Economy?

5.9). NULL HYPOTHESIS EMERGING FROM THE ABOVE QUESTIONS

Recalling the key points about the null hypothesis, we shall therefore state the null as:

1. There is no relationship between Uganda Police welfare and performance in


Lira district of Northern Uganda?

2. There is no relationship between academic qualification level and obtaining


of higher profile job?

3. There is no relationship between judicial reform and service Delivery in the


judiciary sector?

4. There is no contribution of the current numbers of members of parliament to


the performance of all in the Economy.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 20 of 98
6.0) IDENTIFICATION AND ANALYSIS OF A PROBLEM, HOW TO STATE THE PROBLEM

6.1) The Concept of a problem:

A problem is the difference or variation between the actual state of affairs and
desired state of affairs.

A problem results from the recognition of a present imperfection and the belief in
the possibility of a better future.

In relation with research, a research problem has to indicate the possibility of


empirical investigation i.e of data collection and analysis.

6.2) WHAT IS A RESEARCH PROBLEM

A research problem is a demarcation of a situation or problem area within a


certain context involving Who, WHAT, the WHERE, and the why of the problem
situation.

6.3). DEFINING THE PROBLEM AND THE MEANING.

The problem should be differentiated from its symptoms by clear definition, the
definition should therefore clarify the issue at hand and aids the researcher to focus
attention on what is relevant to the problem he/she intends to solve.

The problem uncovers the nature and the boundary including the depth situation,
giving guidance to the researcher to design an appropriate methodology and
sampling method.

It’s further important to note that research questions, Hypothesis and the methodology
are developed from the defined problem.

The evidence that is given in the problem should be a summary of what is already
developed in the background so as to develop coherence, after presenting the
evidence and context then the problem statement can be precise and clear
statement giving the state of the dependent variable being investigated. For
qualitative studies where the evidence is generated during the course of the study, a
researcher can develop hypothetical evidence to that effect, the statement is then
refined as the study unfolds, the statement should clearly disclose the gap that must
be filled by the new generated knowledge.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 21 of 98
Please note that the problem does not necessarily mean something that is negative in
nature, even an extra-ordinary positive behavior of a phenomenon can be referred to
as a problem

6.4). IDENTIFICATION OF A RESEARCH PROBLEM.

1) Review of the existing literature: you many consider reading certain findings and
notice that a certain field or key subject was not covered, this could lead to a
research problem.

2).Theories: Theories is another form of identifying a problem if it has some shortcoming


or leads to certain degree of errors that is not covered in the limit of the accepted
level of accuracy.

3).Personal Experience: Personal experience or the experience of others may lead to


being a source of problem important to research about.

4).Discussion with experts on areas of Concern, this could be in class, targeted group,
seminars, lecture etc.

5). Previous research studies carried out in the field of your interest, a review of these
studies may give a researcher other researchable areas/ projects 6). Media issues.

7).exposure to field situation, Brain storming, Research, intuition etc

6.5).PROBLEM RESEARCHABILITY.

There are some problems that may not be researchable or they may not be worth the
efforts, time and resources, therefore before choosing an area of research it’s prudent
to ask yourself the following questions:

1).Will your research contribute to knowledge and Practice?

2). Will you access the population that you intend to study?

3). Do you have the time, resources and skills needed for the study?

4). Can it prove what you already know?

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 22 of 98
6.6) CHARACTERISTICS OF A GOOD PROBLEM;

1). It should researchable or verifiable

2). It should cover a reasonable scope, i.e not too narrow or too wide.

3). Find answers to problems whose answers have not been found up to present.

4).to review the inadequacies of existing laws, views and policies.

5). to challenge some commonly held beliefs.

6). It should fill a gap or void or extend the existing research 7).

It should be replicable with the new participants or new sites

8). It should give “voice” to people not heard, silenced, or rejected.

6.7) HOW TO STATE THE PROBLEM

1).The statement of the problem involves the demarcation and formulation of the
problem i.e WHO/WHAT, WHERE, WHEN WHY.

2).the problem must present the justification for the problem (based on the past
research and practice)

3). Based on the shortcoming of past research or practice

4).The research problem can be stated in the form of either questions or statements.

6.8). STATEMENT OF THE PROBLEM

The problem statement should close with a question

Typically, the question contains two variables, a measurable relationship, and some
indication of the population.

The research problem should be stated in such a way that it would lead to analytical
thinking on the part of the researcher with aim of the possible concluding solutions to
the stated problem.

The problem statement must provide adequate focus and direction for the research.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 23 of 98
It should also identify key variables and suggest the appropriate methodology for the
study etc

CHAPHER 2
LITERATURE REVIEW IN RESEARCH

Objectives of this chapter:

By the end of the lecture: students should be able to


RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 24 of 98
1).Have basic ideals and tools of reviewing relevant literature to their study.

2).Understand the importance of reviewing literature

3). Know the types of literature review

4). Know and understand the key sources of literature review

5).Understand the common errors in literature review

6).Understand how to handle Citations

2.1. WHAT IS LITERATURE REVIEW

• Mugenda & Mugenda (1999:29) “Reviewing of literature involves systematic


identification, location and analysis of the documents containing information
related to the research problem being investigated”

• Amin (2005:138) refers to it as activity that involves location, reading and


evaluating reports of research as well as reports of observation, discussion and
opinions that are related to the individual’s planned research project.

GENERIC DEFINATION

“Systematic and scientific way of identifying, locating, collecting, organizing and


interpreting of information from documents containing information related to
the research problem being investigated”.

2.2. STAGE OF REVIEWING LITERATURE IN THE RESEARCH PROCESS

Literature can be reviewed at the point when a research idea is conceived,


alternatively the literature available can shape the direction of the study hence review
can be done throughout the process of research.

2.3. PLACEMENT OF LITERATURE REVIEW IN A REPORT OR PROPOSAL

When writing a proposal or report, literature review is usually chapter two (2) of the
entire document, it can as well be put in all the chapters of the research report for
example at the introduction, literature review, methodology and chapter findings and
discussing them. And finally it must reflect the study objectives.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 25 of 98
Carefully read all the articles that concern your subject and mind especially those that
seem to be of interest, where possible repeat the reading on several occasions till you
note down all the important points that are relevant to your research, then analysis
them and make your own conclusion on the article reviewed individually or as a block
representing an objective, you may for instance show whether there are identified
gaps, contradictions, inaccuracy etc.

Literature review lets you gain and demonstrate skills in two major ways:

a). information seeking: the ability to scan the literature efficiently using manual or
computerized methods so as to identify a set of useful articles and books

b). Critical appraisal: the ability to apply principles of analysis to identify unbiased and
valid studies.

2.4. SIGNIFICANCE OF LITERATURE REVIEW

1). Avoids excess duplication of what has already been done: it prevents unwanted
materials from being produced by the research but rather encourages adding
something knew onto what is already existing or allow for minor reproduction but not
100% duplication of already produced findings.

2). Add on the body of knowledge: Literature review also helps to identify the frontiers
of the field and it helps identify how, where and in what manner the proposed
research may add to the general body of knowledge.

3). It helps develop insight on the design of one’s own study showing what approaches
were not successful in prior analyses, or it may show which approaches were not
attempted/ tried.

4). It shows that the researcher is well aware of existing works already researched on in
his or her own area of interest from the perspective of the methods and to find out
problems which remain unresolved.

5).Identifies what the researcher takes to be key issues, the crucial question and trivial
gaps in the current state of knowledge, it forms the foundation upon which all the
future work in the area will be built.

6). It equips the researcher with all the details of related research in progress and not
yet finalized and report pending.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 26 of 98
7). It provides the ideas theories, explanations hypothesis methods of research, key
facts in formulating and studying the problem.

2.5 THE PROCESS OF REVIEWING LITERATURE

1. Identify the literature but only limited to those important and linked to your study.

2. Locate the literature, include the author, edition, page number etc.

3. Record the literature, this will assist you to locate or identify the gaps that will aid
your study.

4. Retrieve the literature

5. Review the literature, objective by objective.

6. Write the literature

2.6 BORG’S (1987) 8 ORDERED STEPS FOR EFFECTIVE LITERATURE REVIEW:

1. Defining the research problem

2. Review secondary source

3. Select and skim through the most appropriate preliminary sources

4. Formulate search words: these are phases that are pertinent to research topic.

5. Search the preliminary sources for the most relevant primary sources

6. Read the relevant primary sources in more detail now, taking notes by used of
notecards 7. Organize the notes

8. Write the report.

2.7). TYPES OF REVIEWS

1. Self-study Reviews: This is the review that is focuses on the researcher’s familiarity
and establishes the credibility of the researcher, in short this increases the
researcher’s self-confidence in relation to what he/she is researching on.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 27 of 98
2. Historical Reviews: This deals with the tracing of the origin and new
development that has been made over time of the subject of study of the
researcher.

3. Theoretical Review: This is based on the theories that form the basis of the
research that is being carried out, it accurately shows the link or the relationship
between the topic of concern and the theory which will in turn make the
understanding of the concept easy.

4. Methodological Reviews: This shows how a given methodology in linked up to


certain study design and its relevance in being used in that particular design.
Therefore depending on the topic of research, it may dictate the type of
methodology to employ.

5. Integrative Reviews: This concerns what is known at appoint in time of the


research

2.8). SOURCE OF LITERATURE IN RESEARCH

1. Primary sources
These are the original work by the researcher or person conducting the study and is
the witnessed by his own eyes at the time of the research. Examples include: Historical
facts, remnant journal articles etc.

2. Secondary Sources

These are second hand information that the person conducting the study may opt to
employ to supplement on the primary sources e.g Books, internet, newspapers,
magazines theses and dissertations etc.

2.9) TIPS ON HOW TO WRITE LITERATURE REVIEWS IN RESEARCH (BASED ON PERSONAL


EXPERIENCE)

1). It’s important to begin with the most recent studies done and then work backwards
to, this is important because it shows the recent scenario where almost everyone is
aware of and assists further in linking the present with the past and thus makes
following the trend of your research easy.

2).Read the executive summary or the abstract of any document first to see if it
addresses your question of concern or study.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 28 of 98
3).Thematically (Make sure that the literature that you are considering is relating to the
specific themes that you are addressing.

4). Makes sure that the works are chronologically arranged.

5). When building your own story, consider areas of consensus in your reviews, consider
areas of divergence as well etc

6). Consider need for a summary on what you have read and backed up by the
evidence in what you have read in the reviews.

GENERAL CONCLUSION ON LITERATURE REVIEW

The important key information after reviewing literature is to ask yourself the following.

❖ What claims or arguments are being made?

❖ Are the arguments logically consistent?

❖ What are the grounds onto which any claims or arguments are made?

❖ What evidence is presented in support of the arguments?

❖ What sources (secondary and primary) have been used?

❖ What are the likely objections that may be raised?

❖ How does the research fit into the field of research?

CITATION AND REFERRING

We always uses APA Referencing which is Harvard style of refereeing, APA stands for
American psychological Association.

Example on citation and referring, Kazungu James Aluko(2016) argues that……………..

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 29 of 98
EXAMPLES OF PROBLEM STATEMENTS

Government of the republic of Uganda has put in place efforts to increase monetary
rewards as motivator for teachers in primary schools. For the last four consecutive years
from 2009/2010 to 2012/2013 financial years, primary teachers’ salaries were increased
as per their grades/ranks. For grade III teachers, salary was UGX 210,000 in FY
2009/2010, in FY 2010/2011 and FY 2011/2012 it was UGX 273,000 and was subsequently
increased to UGX 310,000 in 2012/2013 (Ministry of Public service, circular standing
instructions for financial years, 2009/2010-2012/2013). Government also tried to
increase teacher housing so that they can live near their school, up to 156 houses were
built in the areas of (Bukedea District profile report, FY 2012-2013). It was anticipated to
improve PLE Performance in the government primary schools.

Despite all the efforts by the government, performance of government aided primary
schools is still low, PLE results from the academic year 2012 show that only 10.9% overall
(59,154 out of 543,071) were in first grade(PLE 2012: Performance Report). Physical
evidence from Bukedea district shows a daunting picture with regard to PLE
performance for 2012 as only 92(3.8%) of candidates were in the first grade out of
2866, while in 2011 and 2010 they were 44(1.5%) and 32(1.1%) respectively. This shows
that there is still a problem of PLE performance by the pupils in Bukedea District,
despite the district efforts to improve teacher motivation, little improvement has been
realized in terms of performance at PLE.

It Is Thus hypothesized that teacher motivation in terms of housing conditions,


monetary rewards and teaching materials may partly be a cause of poor
performance which is likely to continue once staff motivation is not prioritized. The
researcher thus seeks to investigate how motivation of teacher affects the
performance of Government aided primary schools with particular reference to
Bukedea District.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 30 of 98
CHAPTER THREE

RESEARCH METHODOLOGIES (STRATEGIES), DESIGN AND TOOLS

3.0 INTRODUCTION:

After reviewing the literature, the researcher is then in a better position to begin
deciding on the research design and methods to employ so as to realize the objective
of his/her studies.

The reviewed literature guides the researcher in the identification of the appropriate
designs/methodologies.

An appropriate design is a critical success factor in research, it’s important to


differentiate between a designs from a method.

A design is a structure of the study, indicating how research resources will be


organized, the respondents grouped, and how variables will be manipulated.

The method is an approach that describes the preferred mode of operation in


conducting a study, a researcher has to decide on the approach to fellow and then
work on the design or structure of how the study will be organized and conducted,
and the design reflects the type of study, objectives and researcher.

A research design explains how the study is to be organized and implemented in


details. It further explains how the sampling will be carried out, how the study group will
be organized, how the variables/groups are to be manipulated and controlled, the
tools for data collection, and techniques of presenting and analyzing data.

3.1 RESEARCH DESIGN EMPHASIZES ON THE FOLLOWING.

1). It may focus on the quality and quantity of the respondents for study (Sampling),
this is the most important component of the design i.e to determine the sample size,
and relevant units that will assist to generate relevant data.

2). the mode of answering research questions or testing hypotheses.

3). the tools to be applied in the research study and their validity

4). the design may also explain the context of the study-surroundings where the
process will be conducted and how the subjects can be motivated to participate fully
in the study. Etc.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 31 of 98
RESEARCH DESIGNS

• Wiersma(2000) defines research Design as the structure by which the variables


are positioned or arranged in the experiment.

• Kumar (2005) Adds that a design is a plan, structure or strategy of investigation,


or the arrangement of the conditions for collection and analysis of data

• Kerlinger (1986) says that it’s the research design that gives research direction
and systematizes it, research design or structure of the research is the ‘glue’ that
holds all the elements in a research project together.

3.2. THE MAIN RESEARCH DESGINS

There are two main overall methodologies (or designs): Qualitative and quantitative.

Quantitative research designs are characterized data or findings which are expressed
in numerical forms, such data are analyzed by suitable statistical methods.

Qualitative research designs are characterized by data (or information) that can be
described verbally or non-numerically, researcher use a mixture of research paradigms
in their studies, this is commonly referred to as triangulation.

A design is used to structure the research, to show how all of the major parts of the
research project –the samples or groups, measures, treatments or programs and
methods of assignments and how they work together to try to address the central
research question.

CATEGORIZATION OF RESEARCH DESIGNS (RD)

1) Experimental

2) Quasi Experimental

3) Non Experimental

1). EXPERIMENTAL RESEARCH DESIGN


Experimental designs provides a systematic and logical methods of answering
questions if it’s done under controlled conditions and what will happen and has the
following characteristics:

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 32 of 98
• It involves carefully manipulating certain variables, treatment or environmental
conditions and observe how conditions or behaviors of the subject are
affected/ changed.
• The design examines the effect of the independent variables on one or more
dependent variables.
• The focus is on the testing of the hypothesis.
• There is total control of extraneous variables.
• The designs enable a researcher to examine issues more critically –to go beyond
description and prediction, beyond the identification of relationships common in
all qualitative studies.

• The groups to be manipulated are equivalent and homogeneous.


• It generates empirical findings that can be generalized with internal and
external validity.
Some of the characteristics of Experimental resign designs
1). Random assignments to the groups
2). Similarity of the subjects.

CATEGORIZATION OF EXPERIMENTAL DESIGNS


There are various types of experimental designs that vary in complexity and quality,
they are mainly differentiated by the number of groups involved.
The validity of the study depends on the match between the comparison groups and
the hypothesis, the control groups in the design greatly strengthen the researcher’s
ability to isolate the casual connection between the independent and the dependent
variables. The common designs under this designs are:
• The post-test only control group
• Two groups pre-test post-test control group
• Two groups pre-test only control group
• Two groups post –test only control group
• Solomon’s four group designs and factorial designs
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 33 of 98
Make Notes on the Above Designs
2). QUASI EXPERIMENTAL DESIGN
These are designs where a researcher do not randomly assign subjects into the control
and experiment group, quasi experiment studies are sometimes called correlational
designs. In this study the researcher is part of the study situation, interacts and
interviews people, has no capacity to control the extraneous variables, this study is
normally conducted outside the laboratory. For example you can conduct a field
study to establish the effects of particular training program using an experimental and
control group. All field studies or experiments fall under this category.
Types of quasi experimental designs includes:
1). One group post-pretest designs
2). One group post -test only
3). Two groups static designs
Please make brief notes on the above

3). NON EXPERIMENTAL RESIGN DESIGNS


These describe the attitude, behavior, characteristics of a group or individual, they are
characterized by non-random assignment. Most studies especially qualitative studies
take up this and has no controlled environment.
Types of research design under this are
1). Longitudinal
2). Cross-Sectional Surveys
3). Case study
4). Descriptive
5). Retrospective
6). Prospective
7).Retro-prospective (retrospective-prospective)

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 34 of 98
LONGITUDINAL STUDIES
This is a study that involves a series of sample measurements taken over a period of
time, the study focuses on a specific respondents or sample over a specific period of
time.
The study examines the behavior of a respondent/groups noting the relevant changes
for example it could be a case study of human development through childhood over
a specific period of time. Or monitoring the effects of ARV on the beneficiaries or how
a certain particular programme impacts on the lives of people over a given period of
time.
Longitudinal studies gives a deeper insight into cases or issues at hand, it may however
give a negative impact or setback if the respondent or participant dies or transfers
before the end of the study.
Longitudinal study is further sub divided into Panel and trend studies.

Panel Study: This occurs when the same group of people or individual is used in the
study, one sample or cohort is studied at different point in time during the study period.

Trend study or time series: occurs when different homogeneous groups or samples are
involved in phases over the study period, and later on the results got from the study
compared and analyzed accordingly. Example of this include classes that change
every academic year, change in level, distribution, relationship and degree.

CROSS-SECTIONAL DESIGNS
A type of survey design that involve a study of sample (s) at the same point in time. The
fundamental difference between cross sectional and longitudinal studies is that cross
section studies take place at a single point in time and that a longitudinal study
involve the series of measurements taken over a longer period.
Cross sectional studies are studies are used in most branches of science, in the social
sciences and other fields as well. Cross sectional research takes a slice of its target
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 35 of 98
group and bases its overall findings on the views or behaviors of this targeted assuming
them to be a typical of a whole group. It may employ a single survey or multi surveys.
A cross sectional of respondents is involved in this study and the respondents are
scattered over a wider geographical area i.e. varying in age groups, tribe, nationality,
religion etc. It’s conducted over a specified and limited time period.

3. Descriptive/cross sectional studies


This is concerned with the describing the characteristics of an event, community or a
region providing data about the population or region studied, the description shows
what, how, when, where, of a situation at a time.

4. Case study
A case study survey studies a social phenomenon through analysis of individual cases,
it could be a person, group, process, community or any other aspect of social life. All
relevant data to the case are collected and organized in relation to the study. The
main advantage of this is that it provides an opportunity for the intensive analysis of
many specific details often disregarded by other methods.
The choice of this design is based on the assumption that the problem under study is
typical of cases of a certain so that after intensive analysis, its generalization will be
applicable to other similar cases.

DESIGNS BASED ON REFERENCE PERIODS 1) Retrospective


This studies and investigates a phenomenon, situation, problem or issues that
occurred in the past, it can be done either based on the data from the period
of time or consulting those who have got knowledge on the same subject
matter.
2) Prospective research designs
This focuses into the future events of the subject matter, the likely prevalence of
a phenomenon, situation, problem, attitude or outcome in the future.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 36 of 98
RETROSPECTIVE-PROSPECTIVE RESEARCH DESIGN
This is one that focuses on the past trend of events of a phenomenon and studies into
the future.
There is a linkage between the past and the future to draw conclusions for example
development plans, we need an analysis of the past to make a better projection.
QUANTITATIVE RESEARCH

Quantitative researches

Experimental Non -Experimental

True Quasi
experimental Correlational Descriptive Casual
Experimental
comparative

Qualitative research
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 37 of 98
Qualitative Researches

Historical Ethnographical Case study Grounded Phenomenological


theory

Ethnographical

Ethnographical is the in-depth study of naturally occurring behavior within a culture or


social group, it seeks to understand the relationship between culture and behavior;
with culture referring to the beliefs, values, and attitudes of specific group of people.
The ethnographic research method was developed by anthropologists as a way of
studying and describing human cultures.

Spindler & Hammond (2000) describes some of the characteristics of a good


ethnography as being

1) Extended participant observation

2) Long time at site

3) Collection of large volume of materials such as notes, audios, video tapes which
means having no specific hypotheses or even highly specific categories of
observations at the start of the study.

Phenomenological design

Phenomenological literally means the study of phenomena. It’s a way of describing


something that exists as part of the world in which we live. Phenomena may be

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 38 of 98
events, situations, experiences or concepts. This branch studies things as they are
perceived not as they are, it begins with acknowledgement that there is gap in our
understanding and that clarification will be of benefit.

Grounded Theory

Based on facts, reasons, reliable evidence which is in touch with reality and at times
it’s based on personal feelings.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 39 of 98
POPUPLATION AND SAMPLING METHODOLOGY

INTRODUCTION

Research has early on mentioned is focused towards the acquisition of information


that is valid, authentic, complete, accurate, verifiable, cost-effective, relevant and up
to date, despite the objective being to produce high quality and timely information,
this goal is hard to obtain without fore going some attributes like injecting in lots of
time, money and other resources.

To minimize costs however in order to obtain acceptable level of accuracy in


information, its completeness, time aspect and update, sampling of the population of
interest is applicable.

Sampling is an act of selecting a small number of objects, subjects, or time frame (from
a population) upon which a research/study will be conducted to represent the entire
population of interest. Then a representative sample is chosen from the entire
population and thus tested, the result of the sample is assumed to represent the whole
population, in reality, the bigger the sample size, the higher the level of accuracy.

A population can be defined as including all the people or items with all the
characteristic one wishes to understand, it could be a complete set of individuals,
objects, or cases with some common observable characteristics

A population can as well be defined as the total of items or events in a set with
relevant characteristics that the researcher needs to aid in the study, it’s the total
number of potential subjects/respondents for the study. Population can be
categorized as Heterogeneous or Homogeneous, target or accessible, definite or
indefinite.

Heterogeneous population: This population consists of subjects/respondents


differentiated by specifiable features for example, status in society, age, sex,
educational background etc. A heterogeneous population is difficulty to study
effectively coz it requires a bigger population sample than that of homogeneous
population and diverse responses are expected from a variety of respondents thus
validity of information may need a bigger sample size.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 40 of 98
Homogeneous Population; this is a population that has specific characteristics in
common to that which the researcher requires in the sample to be studied, it requires
a smaller sample since its assumed to be homogeneous, even a smaller samples
opinions may effectively represent those of a population.

Target population: target population or ideal is the one that a researcher would
effectively apply in a study but is rarely available for study, it’s the ideal choice one
would wish to have but not accessible, these could be people scattered over a wider
geographical area which a researcher cannot access. It’s an indefinite population.

An accessible population: This is the population that is readily available and can be
easily identified, with a sample frame and specific characteristics, it represents a
realistic choice, and this is a defined population.

Definite population is accessible, and with a specific sample frame of units with
appropriate contact information to enable random sampling –all members of that
population are known and thus a researcher can easily manage it for example all the
teaching staff of Kyambogo University, Faculty of Engineering or members of an
association.

Indefinite (target) population is not easily determined or accessible i.e. its members are
not defined for examples Numbers of secret admirer to someone, (you do not how
many people admire you, another example is number of homosexuals in KYU or gays.

THE GUIDANCE TO DECISION ON SAMPLE SIZE AND METHODS

• The type and purpose of research being carried out

• The degree of accuracy or confidence levels required in a research

• Cost and time considerations

• Levels of destructions involved while sampling

• Time of dissemination of results

• Size and nature of the population to be sampled: homogeneous,


heterogeneous dispersed. Etc.

• The type of research designs/ methods to be applied (experimental or


nonexperimental.

• The geographical dispersion(size of the area for study)


RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 41 of 98
DEMONSTRATION ON TARGET POPULATION, ACCESSIBLE POPULATION AND SAMPLE

TARGET POPULATION Students in the Faculty of Engineering

at Kyambogo University (N=8,000)

ACCESSIBLE POPULATION Students of B.Eng. CBE (N=500)

SAMPLE Sample randomly selected B.Eng. III (n=80)

DETERMINATION OF SAMPLE SIZES

1) Non mathematical or convenience methods where the sample is determined at


the discretion of the researcher

2) Statistical methods – using formulae

3) Statistical tables

SAMPLE SIZE SELECTION

(i) Use of a formular n = N

1+ Ne2 where n, represents desired sample size, N represents


population size and e represents degree of freedom/level of precision, which
is 0.05 (Yamane, 1967)

(ii) Use of sample selection table (Krejice and


Morgan table of 1970)

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 42 of 98
SAMPLING TECHNIQUES/PROCEDURE

This is the description of the strategies which the researcher will use to select
representative elements/subjects/respondents from the target/accessible population.

To select a representative, the researcher must have a sampling frame

• It is a list, directory or index or cases from which a sample can be selected

• Subjects or cases selected from the sampling frame the units of observation in a
study

SAMPLING STRATEGIES/TECHNIQUES

There are majorly two strategies in sampling

1) Probability based sampling

2) Non – probability sampling

PROBABILITY BASED SAMPLING

Choosing a study sample is an important step in any research since its rarely practical,
efficient or ethical to study the whole population. The aim of quantitative sampling
approach is to draw a representative samples from the entire population so that the
results of studying the sample can then be generalized back to the population.

Probability sampling is one in which every unit in the population has a chance greater
zero or being selected in the sample and this probability can accurately be
determined. There are a number of probability sampling techniques:

1) Simple random sampling

2) Systematic random sampling

3) Stratified random sampling

4) Cluster sampling

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 43 of 98
SIMPLE RANDOM SAMPLING

This is a sampling technique that gives equal and independent chance to all the
members of a finite population to be included in a sample, it’s a purely random
method where every item in a population is chosen on a probability basis.

Procedure

• The table of random numbers is often used in the selection of a random sample

• Obtain a list of accessible population

• Assign numbers to each subject

• Using a table of random numbers, randomly select a raw or column as a starting


point

• Select all the numbers that follow in the column

• If you need more numbers you can proceed to the next column until you have
enough to make up the desired samples

Note: Here it’s important a rotary method or a table of random numbers is applied to
ensure the unbiased selection of items

SYSTEMATIC RANDOM SAMPLING PROCESS

• List all the members in the sampling frame in a random order

• Determine the sample size

• Determine the sampling interval (distances between cases selected for


sampling)

• Sampling interval (K) = total population


Sample size

• Blindly select the starting point from the random numbers

• Every kth element of the population frame is selected for inclusion in sample.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 44 of 98
WRITING A RESEARCH PROPOSAL
A research proposal is a document which gives an account of what will be
investigated and detailed plan of action, it’s generally the first step in developing a
research project.

Research proposal can as well be defined as “A written presentation of an intended or


planned process that the researcher will take in the process of solving an identified
research problem or gap”.

The process of preparing a proposal should be based on a detailed, relevant reading


and citation of the relevant literature in the study field.

The research proposal outlines the specific aspects and activities of the research
process, the proposal should clearly spell out the research problem, objectives,
research questions/ hypotheses, theoretical/ conceptual framework, significance and
scope of the study including limitations of the study, operational definitions and terms
and finally the methodology that will be used to gather and analyze it.

1. THE MAIN OBJECTIVE OF A RESEARCH PROPOSAL

The main purpose of a research proposal is to demonstrate that the person intending
to do the research or study (the researcher) has a clear conceptualization of the
research problem and the research process and above all to show that he/she has
done enough reading with relevant information about the recent work done in the
area of interest.

2. REASONS FOR PROPOSAL WRITING

1. To communicate the researcher’s research plan to the institution or individuals


who provide evaluative feedback or give permission for the research to be
conducted or for the proposal to be registered for award of a given honor in a
given discipline.

2. It presents an agreement between the person who authorizes the study and the
researcher to the problem to be investigated on.

3. It gives the opportunity to the researcher to organize clearly delineating his or


her ideas

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 45 of 98
4. It provides a detailed plan of investigation and incorporates anticipations of
problems to be handled and contingent course of action. Etc.

5. CONTENTS OF A RESEARCH PROPOSAL

The structure and the format of a research proposal vary from researcher to researcher
or from one institution to another, the basic principles however remain the same.

The following are the basic contents of a research proposal.

The title of the proposal and include:

a) The title page: the title of the study should be on the first page, it should be
written in a symmetrical manner and centered.

b) Author’s name: the name of the person who has written the proposal must
appear with the order of the first name, surname. Etc.

c) Qualification requirement (Degree, Diploma etc)

d) The purpose of the proposal and the name of the awarding institutions ( for
academic purposes)

e) Date of submission, months and year.

Table of content

This appears on the second page of the research proposal, this page appears in
roman numbers and covers the outline of the proposal indicating on which page
each major chapter, section and subsection is located.

CHAPTER ONE

1.0 INTRODUCTION

This tells the reader what the study is all about, the variables of the study and how the
chapter is organized for example this study is to explore the relationship risk
management and performance of National Water and Sewerage Corporation,
Central Region.

In the above study risk management is conceived as the independent variable (IV)
and performance as the dependent variable (DV)
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 46 of 98
1.1 BACKGROUND TO THE STUDY

The back ground of the study helps the reader to understand the problem by
describing how the problem was identified and linking the problem historically to the
professional field or area of interest. It is a narrative of facts that explain what is true or
what is taking place before you start to state what is disturbing you that is worth
research.

It introduces the background of the problem and shows it on the international and
national perspectives, it contains the context of the study to be conducted to cover
the cultural, economic and social situation.

The background may be funnel-shaped in the sense that it locates the study within the
global perspectives, and narrows it down to the regional, national and finally the local
context (Mugenda and mugenda, 1999) or should give the historical, theoretical,
conceptual, and the contextual background (Amin, 2005)

1.2 STATEMENT OF THE PROBLEM

This is the gist of the research, a phenomenon for which you need an explanation or a
knowledge gap that you need to address.

The problem should be stated clearly and consciously by identifying the dependent
and independent variables of the study.

The researcher must know and present the evidence of the problem than just basing
on the allegations but should rather be factual, figures and statistics can also be
presented to show a backing to the problem, this statement should not exceed one
an half pages in a report and rather better half a page in a proposal.

1.3 PURPOSE OF THE STUDY

This states clearly what the research is intended to serve or to investigate. It is the
general description of the overall aim. It should specify the variables that the
researcher wants or intends to focus on.

1.4 OBJECTIVES OF THE STUDY

These are fine statements that show what is to be achieved at the end of the study,
they refer to specific aspects of the phenomenon under study that the researcher

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 47 of 98
desires to bring out at the end of the research study, objectives may be sub-divided
as:

General objectives: This is the overall purpose of the research, it shows clearly what the
research is to investigate and accomplish. This is normally a paraphrase of the title and
introduces the independent and dependent variables.

Instead of using the general objectives of the study you may use the purpose of the
study, which serves the same purpose.

Specific objectives: These are refined statements that show what is to be achieved,
they are refined from the general objectives and they break down the general
objectives into smaller and concise statements that the researcher intends to achieve
at the end of the study.

The specific objectives should be extracted from the research problems and they
should not exceed 3 because they may increase the work load of the researcher.

It’s important to note that: if you use General objectives of the study, then you next sub
heading must be the specific objectives of the study and if you use the purpose of the
study then you next sub-heading becomes the objectives of the study.

1.5 RESEARCH QUESTIONS /HYPOTHESIS

Research questions involves restating objectives of the study in question form, the
questions should not exceed the numbers of the objectives and should be clearly
stated.

A researcher instead of using the research questions, he/she can state research
hypotheses, a research hypothesis is a tentative preposition suggesting a relationship
between the variables or a predetermined answer to the research problem but
pending verification.

However some studies may demand both the research questions and hypotheses to
be used in the same study, therefore we shall adopt the approach of using both.

1.6 CONCEPTUAL FRAMEWORK

Research is based on the conceptualization of a pertinent problem and relationships


between variables and how they impact or affect one another.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 48 of 98
A conceptual framework is a diagrammatic representation of the relationship
between variables and how they are operationalized for the purpose of research. It
should indicate the independent and dependent variables (cause/effect relationship)
or moderating and intervening variables where applicable.

1.7 SIGNIFICANCE OF THE STUDY

This refers to the relevance of the study in terms of the academic contributions and
practical use that might be made of the findings to the organization/sector in which
the researcher is based and to the public at large.

The researcher must tell the readers the reasons as to why and how he/ she thinks the
findings might change polices, theory or practice. In short should indicate who should
benefit from the study and how,

1.8 JUSTIFICATION OF THE STUDY

Research justification states why the study is wanted , it highlights the potential values
of the study and also shows to whom the study results will be of importance, showing
the ways and how

1.9 SCOPE OF THE STUDY

This states out the limit of the study, the scope basically has three dimensions:

Geographical: this shows the geographical boundaries of the research/study, if a case


study is used, then the geographical scope specifies the location of the case of the
study.

Content scope: this can also be called the subject scope and it points out the area in
terms of content or concept being investigated.

Time scope: This spells out the time limit in terms of data that will be used in the study.

CHAPTER TWO: LITERATURE REVIEW

• This section reviews literature that is available in relation to the study that the
researcher is conducting, the literature must be related to the problem.

• This is the heart of any research study, the review indicates and covers:

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 49 of 98
• The introduction to the chapter

• What others have said and written about the subject that you are investigating
on

• The relationship between the independent and the dependent variables in the
study.

• It shows whether there has been any research work in the field you are
investigating and the findings.

• It indicates the knowledge gaps that need to be fulfilled.

THE STRUCTURE OF LITERATURE REVIEW

2.0 Introduction

This chapter like any other chapter begins with the introduction, here you are trying to
inform the reader what to anticipate as he/she advances with the chapter and how
the chapter is organized.

2.1 Theoretical review

Under this sub-heading you ought to give a detailed explanation of the theory you
gave in the theoretical background in a detailed way and the relevance of the theory
in line with your current subject of study.

2.2 Actual literature

This is based on the sub-headings derived from the objectives of the study.

2.3 Summary of literature.

Here you ought to summarize the literature reviewed and identify the gaps to guide
your study.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 50 of 98
CHAPTER THREE

METHODOLOGY

This section answers how you are going to carry out the study, it gives the details on
how you intend to conduct your research. The following should be included on the
methodology.

3.1 Research Design

In this subsection the researcher identifies the type of a design (plan) to be used and
gives the reason for the choice. Some of the common research designs include: cross
sectional design, longitudinal design, surveys and case study design etc.

3.2 The Study Population

This subsection clearly indicates or shows who will participate in the study and how the
sample will be collected or selected. It indicates the number of subjects (elements)
that will be covered by the study.

3.3 Sampling Methods

The researcher explains how he or she will select the elements from the study
population, for example whether to use random sampling or non-random sampling
methods and gives the reason for the selection.

3.4 Structure of the Sampling Size

This describes the composition of the sample size, i.e how many elements may be
represented in each sub sample/category of the population.

3.5 Data Collection Methods

This includes the specific techniques to be used in the collection of data, data
collection methods include: interviews, focus group discussions, questionnaire, surveys,
observation, document review etc.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 51 of 98
3.5.1 Data Collection Instruments

Any appropriate tool that is used to collect data is referred to as data collection
instrumentation. They include: interview guide, questionnaire, key informants’ guides,
and focus group discussion, check list, observation checklist, document review
checklist etc.

3.6 Validity and Reliability of Data

Data collection instruments should be tested for their validity and reliability to ascertain
whether the findings can be accepted or not

Reliability of an instrument is the consistence/dependability of an instrument in


measuring what it is designed to measure and on the other hand the Validity of an
instrument is the extent to which an instrument measures what it is designed to
measure and measuring it accurately.

Pretesting of an instrument can be used to guarantee the validity and reliability.

3.7 Measurement of Variables

The researcher should state how he/she intends to measure the variables in the study
I.e the dependent and the independent variables. Suppose you have performance as
your variable then you should state how you will measure performance, performance
may be measured as:

• Profitability

• Increased product demand

• Financial sustainability.
3.8 Data Analysis

In this section the researcher should indicate how data will be analyzed once
collected. If the data is quantitative in nature, this requires a quantitative analysis, then
the researcher should indicate the statistical technique to be used for the analysis.

In most cases more than one methods of analysis is used, it’s important to note that the
method of analysis chosen depends on the type of research, the objectives and the
hypotheses to be tested.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 52 of 98
Finally the researcher must state what he/ she hopes to achieve by using the data
analysis technique chosen and pointing out the advantages for the selected
techniques over others methods is key.

3.9 Anticipated problems (Limitations of the study)

Limitations are the problems that a researcher is likely to face during the research
process. They refer to the conditions that are beyond the researchers control and
which are likely to impact on the research study, they include: limited funding, limited
time, limited access to respondents where people may not willing to give some
information.

3.10. Ethical Considerations.

Issues like privacy, who will be accessible for data, how will informed consent be
obtained?

3.11. Time Frame/ schedule

A time schedule refers to how long a researcher will take to finish the research.

This is very important component for both new and experienced researchers in that it
makes you utilize well the time frame and produce wanted work in the given period.

In most cases, the funders have deadlines to stop funding the research and as such a
dead line should be adhered to.

Similarly students also have a time frame or deadline to finish their work and this guides
them in formulating schedule, time schedule also lists activities and their corresponding
time period for an activity to be complete.

Time frame is usually given in months or weeks and it’s important to note that most
activities can overlap, so the one that does not have to finish one activity so as to start
another or the next one.

3.12 Budget

A budget is the list of the items that will be required to carry out the research and their
approximate cost.

The budget should be well thought out to avoid asking too little or too much, if the
research is to be submitted for funding, it is advisable to include all the requirements.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 53 of 98
The budget should be detailed enough and precise on items needed, prices per unit
and total cost.

3.13 Appendix

This contains the information that the researcher does not deem necessary to include
in the main body of the report.

These are things that make the report unnecessarily long and non-value adding and
appending them is the only option.

These may include-instruments used, statistical tables, correspondence related to the


study, maps etc.

STRATIFIED RANDOM SAMPLING

This is another approach to random sampling through some stratifying technique, in


this method a heterogeneous population with identifiable sub groups is divided up into
categories/strata according to particular criteria. The strata must be mutually
exclusive. The handling of each category proportionally (basing on strata size), each
stratum is then sampled as an independent sub population- individual. Individual
elements are randomly selected from each strata.

This method reduces the weaknesses of simple random sampling, it considers every
major stratum (sub-groups within a heterogeneous population) each group is
represented proportionally basing on the sample size and number of units in a sub
group. It is good for populations of heterogeneous nature.

Key Caption on The Above

This concerns the heterogeneity of the populations to be sampled-achieve desired


representation.

The population is divided into sub-populations such that the elements within each are
homogeneous.

Simple random samples are then selected independently from each sub-population.

PROCEDURE OF STRATIFIED RANDOM SAMPLING

• Identify the population


RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 54 of 98
• Define the criterion for stratification

• List population according to defined strata

• Determine the required sample size and appropriate


representation
(appropriate or variability)

• Select using random numbers, an appropriate number of subjects.

ADVANTAGES OF STRATIFIED SAMPLING

1. Stratified sampling focuses on important sub populations an ignores irrelevant


population

2. Allows use of different sampling techniques for different sub populations

3. Sometimes data is more readily available for individuals, pre-existing strata within
a population than for the over role population.

4. It improves on the accuracy/efficiency of estimation

5. More efficient statistical estimates (provided that strata are selected based
upon relevancy to the criterion in question instead of availability of the samples

Disadvantages of stratified sampling

1. Requires selection of relevant stratification valuables which can be difficult

2. It is not useful when there are no homogenous sub groups

3. Can be expensive to implement

Cluster sampling

This is a sampling method whereby a research divides a population into clusters basing
on specific criteria and then sample units are randomly selected from the cluster.
When the clusters are geographical, the sampling is referred to as territorial. It almost
resembles stratified sampling.

• Sometimes it is cheaper to cluster the sample in some way e.g. by selecting


respondents from certain areas only

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 55 of 98
• Used when it’s not possible to obtain a sampling frame because the population
is either very large or scattered over a geographical setting.

• It involves selection of an intact group

• Elements of a population are grouped into clusters and simple random sampling
or any other type performed on the clusters

Steps in cluster sampling

1. Identify the population

2. Define the cluster forming the population

3. Determine the required sample size

4. List all the clusters in a random order

5. Use the table of random numbers, select the required numbers of clusters
according to the sample size required

6. All the members in the selected clusters are included in the sample.

TWO MAIN STRATEGIES TO SAMPLING

Recall that we have two main strategies of sampling, namely: Probability based
sampling and Non-Probability sampling.

NON-PROBABILITY SAMPLING

Non probability sampling techniques focus on in-depth information,


not generalizations of the studies and elements in the population do not have a known
probability of being selected.

Representativeness of the sample is not the issue in this technique.

Samples may include volunteers, easily available units or those who happen to be
available or present at the time when the research is being carried out.

TECHNIQUES OF QUALITATIVE SAMPLING

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 56 of 98
CONVENIENT SAMPLING

This involves selecting cases or units of observation as they become available to the
researcher.

Sampling is done to whoever happens to be available at a given moment to the


researcher.

This happens to be the least rigorous techniques because it involves selection of the
most accessible subjects.

It’s the least cost to the researcher in terms of time, effort and money.

PURPOSIVE SAMPLING

This type of sampling, the researcher uses his/her own judgment/experience in


selecting elements in the sample

The researcher further actively selects the most productive sample to answer the
research questions

The elements here are handpicked because they are either informative or have the
required characteristics and further specify the criteria for selecting a particular
sample

QUOTA SAMPLING

• This includes various groups or quotas of the population in the study based on
the same criteria.

• Often used in the survey research where it’s not possible to list all the members of
the population of interest.

• The researcher purposively selects subjects to fit the quotas identified.

• Data is obtained from easily accessible individuals.

SNOWBALL SAMPLING

This involves asking a key informant for other people who should be contacted by the
researcher.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 57 of 98
Individual subjects with desirable characteristics are identified first, who name others
until the researcher gets the required numbers of respondents.

Useful when the population that possesses the characteristics under study is difficult or
impossible to locate.

DATA COLLECTION

Data collection exercise commences at the time when a research proposal is


approved by the authority, at this time an appropriate research tools are designed
and pilot tested. The exercise can be rather interesting or challenging depending on
the type of research designs, geographical coverage, and level of preparation and
comprehension of the whole exercise.

DATA SOURCES

There are three sources of data that can be used in research:

Primary data (original data from the live events for example through interviewing and
observation or diary methods, secondary data and tertiary data, primary data
collection picks novel or originated data that directly related to the topic under study,
data from for example original manuscript, classical literature, source documentation
in recording of transactions/events, it could also be data recorded during or after an
observation events to get fresh facts related to your subject of concern.

Secondary data: this is data collected from work of others that may not be directly
related to the subject or topic of your study, it provides criticism or interpretation of the
primary source, this is data collected from records of events that happened.

It is always important for the researcher to give reference of the source of data so as
to give credit to the people who collected data and compiled it. Secondary data is
mainly collected from print media, in libraries or files of companies, the internet or
testimonies of people through their experience. Secondary data are used for purposes
other than those of which they were intended.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 58 of 98
Quoting sources (A.P.A Styles)

Whenever researcher uses another person’s ideas in research, he/she must quote the
source of the data from the source, and in the reference section at the end of the
papers, there are two major methods of referencing or quoting sources of data
however we shall limit our research to the A.P.A (American psychological associations)
rather than MLA

DATA COLLECTION METHODS AND INSTRUMENTS IN RESEARCH

Research collects both qualitative and quantitative data using various methods and
instruments, the choice of the method/instruments depends however on the Sample
size, the characteristics of the respondents, source availability and convenience of the
researcher. Some of the methods are discussed here under:

1). OBSERVATION METHOD

This is the method by which an individual/individuals gather firsthand information on


programs, process or behaviors being studied.

This is the systematic selecting, watching and recording behavior and characteristics
of living beings, objects or phenomena.

Observation of human behavior is a much used data collection technique and can
be divided into the types as:

1). Participant Observation.

This is the situation where the observer takes an active part in the situation that he/she
is observing for example a University Lecture who observes a university procedures
from within or a magistrate who observes court proceedings from within .etc.

2). Non-Participant Observation:

The observer watches the situation openly, or concealed, but does not participate. 3).

Contrived Observation (Laboratory Observation)

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 59 of 98
OBTRUSIVE AND UNOBTRUSIVE METHODS OF OBSERVATION

Obtrusive: Observations are made of behavior with the participant’s knowledge


(interviews, surveys, focus group)

Unobtrusive: observations are done without the knowledge of the participants

For example watching a participant from a distance, Historical/ Document/Archival


data.

ADVANTAGES OF OBSERVATION METHOD OF DATA COLLECTION.

• It fives an additional and more accurate information on the behavior of people


than interviews or questionnaires.

• Can check on the information that is collected through interviews especially on


sensitive topics i.e. Drug use, stigmatizing diseases-AIDS etc.

• This methods provides first-hand information i.e. presence of something and its
state.

• Approaches reality from its natural setting and study events as they evolve.

• Items exist in a natural, unstructured and flexible setting.

DISADVANTAGES OF THE OBSERVATION METHOD

• Observer bias may occur

• Requires thorough training of researchers

• Presence of data collector may influence the observed situation

• Ethical issues may arise regarding confidentiality and privacy

• Time consuming and laborious method

• This method offers no control measures regarding bias, attitudes and opinions of
the observer.

• Cannot provide information about past, and the future.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 60 of 98
2). INTERVIEWING METHOD OF DATA COLLECTION

An interview is a dialogue between the interviewers and the interviewee for the
purpose of gathering data from the respondents, this is the most flexible method that
can adjust to the world of participants with less or no inconveniences in terms of venue
format etc, it can be conducted from anywhere to accommodate the respondents’
needs.

For an interview to become more successful, both the parties must be ready and
interested in the exercise, the interviewer must have the relevant skills to conduct the
interview and the interviewee must be ready to offer information and correctly.

TYPES OF INTERVIEWS

Interviews are categorized under three major areas based on their level of formality
and how questions are prepared, they may include:

• Formal or informal

• Structured or not structured

• Directive or non-directive

• Personal (face to face)-Non personal (through a medium like a phone)

Formal interviews are structured in nature: they are conducted in a formalized way or
in a specific way or order of questions, the questions are specified, and structured in a
questionnaire form. The exercise follows a specific order with each respondents going
through the same questions. The purpose of the interview is to a certain extent
standardized in content, time and scoring. It could be conducted by one person or by
a panel of interviewers.

Informal or unstructured interviews: They are interviews that lack elements of


standardization, questions are not prepared in advance they flow spontaneously from
the interview context, and the direction of the question is created by the interviewee.
The question for different respondents are May or may not be related, the time,
content, venue, and score are not decided upon in advanced. One person normally
conducts such interviews in an informal way. That is no order in the questioning, no sign
of noting down responses, or no asking questions that are related to specific topics.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 61 of 98
Directive interview (structured): The interviewers keeps the exercise in pre-determined
parameters and asks questions in specific format. A non-directive interviews
(unstructured) on the other hand allows spontaneous development of ideas and
feeling through indirect questioning, and building of trust and confidence of
interviewee.

Interviews can be conducted with varying degree of flexibility, the two extremes are
high and low degrees of flexibility

High Degree of Flexibility:

• This is used when studying sensitive issues such as teenage pregnancy and
abortions.

• This approach is as well used when the researcher has limited understanding of
the problem or situation that he is investigating.

• Investigators may use a list of topics rather than fixed questions

• Sequence of topics should be determined by the flow of discussion.

• Instruments used may be called an interview guide or interview schedule.

Low degree of flexibility

• This is useful when the researcher is relatively knowledge about expected


answers

• When the number of respondents being interviewed is relatively large.

In practice it’s important to be positive in while in an interview:

• Maintain eye contact

• Keep a natural role

• Ask open ended questions

INTERVIEW SKILLS

• Clothing of interviewers should be culturally accepted and as simple as possible.

• Sitting arrangements for interviewer(s) and informant(s) should be strategically


and friendly arranged so as not to scare the respondents and vice visa.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 62 of 98
• Issues relating to gender has to be respected

• Community participation/Environment should also be supportive of the interview


situation.

INTERVIEWING TECHNIQUES

• Ask one question at a time

• Repeat questions where if necessary

• Allow respondents enough inn answering or responding

• Avoid suggesting answers to respondents

• Don’t react to answers

• Don’t be controversial to the respondents

• Take key not of answers that are ambiguous

• You can use the following formula or approach to generate open questions i.e

T= Tell me more about this situation

E=May you explain further please

D=Describe the situation more please my dear

• Why questions is always less accepted and often arouses a feeling of intrusion.

Advantages of interviewing

• Provides an in-depth data on the subject at hand (Mugenda and Mugenda ,


1999, P.38)

• Allows flexibility in questions to the subject of interest

• It’s an appropriate method with the illiterate population

• Has the ability to record visually seen responses

• Respondents are not constricted as the questionnaire

• Has Viable, rich data and spontaneous responses

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 63 of 98
DISADVANTAGES OF INTERVIEWING

Expensive in terms of time, cost of training interviewers, source consumption) Requires

high skills and expertise in conducting it.

3). QUESTIONNAIRES SURVEY

This is a data collection tool in which written questions are presented to be answered
by the respondents, a written questionnaire can be administered in different ways:

1). Sending questionnaires by email with clear instructions on how to answer the
questions and asking for mail responses.

2). Gathering all or part of the respondents in one place at one time, giving oral or
written instructions and letting the respondents fill out the questionnaires.

3). Finally hand-delivering questionnaires to respondents and collecting them later.

Class Discussions One

QUESTIONNAIRE CONSTRUCTION

The following are key in construction of questionnaires in research: Length, Content,


Language, and specificity, avoid Void words and questions finally leading questions
must be avoided eg……….

ADVANTAGES OF QUESTIONNAIRE

• They are less expensive in data collection compared to other methods

• Its best for sensitive or personal questions

• They is no interviewer bias

• They is permanent anonymity and may lead to more honest or reliable data.

• This methods may not require research assistants.

• The questions can be administered over a wide distribution

• It brings out considerable objective views of the respondents.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 64 of 98
DISADVANTAGES OF THE METHODS

• This cannot be used on illustration

• Questions may be misunderstood and thus wrong answers obtained.

• They is usually a low rate of response from the respondents.

• They is long response time from the target population.

• No ability to probe on open-ended questions

• Cannot confirm who actually who answered the question

IMPORTANT ISSUES IN CONSTRUCTION OF QUESTIONNAIRE

1. Select an appropriate name for questionnaire, the name should appear in such
a way that it will attract the respondents to fully participate in the exercise e.g…

2. Explain the purpose of the questionnaire to the respondents clearly, this will lead
to openness in information being given.

3. Instruct the respondents on how the responses should be made.

4. You must set simple and clearly questions or statements and with simple
understandable languages.

5. Avoid questions or statements that collect unnecessary personal information


from respondents. Eg how old are you to day but instead give rages or
categories.

6. Avoid negativity-especially double negativity in constructing an item.

7. Avoid negative questions.

8. Avoid double or multi-barreled question.

9. Use correct language and spellings

10. Make your questionnaire neat and orderly

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 65 of 98
CONDITIONS FOR USING THE QUESTIONNAIRES

• When the population is big and dispersed over a geographical area.

• When the population is literate

• When the sample is specialized or professionals

• When there are budget constraints to reduce costs

• When a moderate response rate is considered successful or satisfactory When

the ease of administration is prerequisite for a successful study.

4). DOCUMENTARY REVIEW

Kothari, (2004) states that when the researcher utilizes secondary data, then he/she
has to look into various sources where he is certain to obtain data, in this case Kothari
further contends that the researcher avoids problems associated with collection and
analysis of original data.

Mugenda and Mugenda, (2003), says using document review as a method of data
collection helps the researcher to avoid duplication of work done by other
researchers.

5).FOCUS GROUP DISCUSSION (FGD)

Focus Group: here an interview is conducted among a small number of individuals


simultaneously; the interview relies more on group discussions than on directed
questions to generate data.

Characteristics of focus groups

• Typically 8-12 people

• Homogeneous within a group

• Duration of the session is between 1.5hours to 2 hours

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 66 of 98
• Sessions recorded and transcribed.

• Moderated group discussions on a particular topic/issues

• It allows for a group of 8-12 informants to freely discuss a certain subject with
guidance of the facilitator or reporter.

• Usually conducted with targeted samples of stakeholders, such as staff,


administrators, families, funders and community members.

• Usually held in an informal setting and are moderated by the researcher

• Select a small group of participants, not more than 15 people

• Set clear guidelines from the beginning

• Ensure equal participation

• Encourage equal discussion of the participants

• Encourage involvement of all parties

• Avoid being placed in the role of being an expert.

DATA COLLECTION INSTRUMENTS

The following are some of data collection instruments:

• Interview guide or interview schedule

• Observation schedule

• Check list

• Library search

• Tests

What makes a focus group participation complete

Moderator

Moderator’s Guidebook: Funnel Approach is encouraged, here we start with a broad


questions or tasks, then narrow down to the topic at hand in the local perspectives.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 67 of 98
Characteristics of a good moderator

• Superior learning ability

• Excellent short-term hearing memory

• Well organized

• Quick leaners

• High energy level

• Friendly to the participant

ADVANTAGES OF FOCUS GROUP DISSCUSSIONS

• Small focus group discussions may increase the comfort level of participants

• Quick/fast in deliberations and feedback response

• Firsthand information is obtained.

• Presence of many or several respondents at the same time provides a certain


level of synergy

DISADVANTAGES OF FOCUS GROUP DISCUSSIONS (FDGS)

• Can be difficult to elicit participants from individuals who have time constraints

• May involve high costs (organization and facilitation)

• Scarcity of good professionals to conduct the interviews and discussions

• Some participants can dominate the conversation

• Multiple participants can also make documentation difficult

• Focus group cannot deliver final results or answers to decision problems.

CONSTRUCTION OF QUESTIONNAIRES, THIS WILL BE DONE WITH HANDS ON PRATICALES


IN CLASS.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 68 of 98
RELIABILITY AND VALIDITY IN RESEARCH.

Reference is made to various data collection methods that we have already


concluded in our previous chapter, it was noted that the quality of research depends
to a large extend on the accuracy of the data collection procedures. That is to say
the instruments or tools that are used for data collection must yield the type of data
that the researcher can use to accurately answer his or her questions. Irrespective of
whether one is using a self-developed questionnaire, interview schedule, observation
checklist or standardized test, the data so obtained must be pertinent to the research
hypotheses.

When conducting a research we try as much as possible to maximize the reliability and
validity of the data collected. For reliability and validity to exist in the data, the data
collection techniques must yield data that is not only relevant to the research
hypothesis but also correct.

Reliability and validity are the measures of this “relevance” and “correctness”

RELIABILITY OF DATA

Reliability is a measure of the degree to which a research instrument yields consistent


results or data after repeated trial. Reliability in research is influenced by random errors,
as random errors increases, reliability decreases. Random error is the deviation from a
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 69 of 98
true measurement due to factors that have not effectively been addressed by the
researcher. Errors may arise from inaccurate coding, ambiguous instructions to the
subjects, interviewer’s fatigue, interviewee’s fatigue interviewer’s bias, etc. in a nut
shell random errors will always exist regardless of the procedures used in the study
(Mugenda and Mugenda 2003)

It’s important to note that research instruments yield data that have two components:
the true value or score and an error component. The component of the data reflects
the limitation of the instrument.

They are three types of random errors that arise at the time of data collection:

• Errors due to inaccuracy of the instruments


• Errors due to the inaccuracy of the scoring by the researcher and
• Unexplained errors

These errors combined produce inconsistencies in the measurement which hence


affect reliability of the data collected.

The research process attempts to minimize random errors and hence increases the
reliability of the data collected. In a research study, a reliability coefficient can be
computed to indicate how reliable data are, a coefficient of 0.80 or more implies
there is a high degree of reliability of the data.

There are four different methods of assessing data reliability and each deals with a
different aspect of the concept.

The Test-Retest Technique

The test-retest method of assessing reliability of data involves administering the


same instrument twice to the same group of subjects. There is usually a time lapse
between the first test and the second test. The test-retest method involves the
following steps:

1). Select an appropriate group of the subject.

2). Administer the test to the subject.

3). Keeping all the initial conditions constant, Administer the same test to the same
subject. The spacing between one tests to another may take about four (4) weeks.

4). Correlate the scores from both testing instruments.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 70 of 98
The correction coefficient obtained in the above is referred to as “the coefficient of
reliability or stability”. If the coefficient is high, the instrument is said to yield data
that have a high test-retest reliability.

The disadvantages of this method of assessing reliability of data are that subjects
may be sensitized by the first testing or they may tend to remember their responses
during the second testing. If that happens, the coefficient may be artificially high.

The other difficulty with this method is establishing a reasonable period between
the two testing sessions, if the period between the sessions is too long, subjects may
have changed or other extraneous factors may interfere with the variables being
measured. The computed coefficient of stability in such cases may be artificially be
low or high.

The Equivalent-Form Technique

The problems inherent in the test-retest method are to a certain extent taken care of
by the equivalent-form techniques of estimating reliability. This approach uses two
equivalent instruments. Specific item in each form are different but are designed to
measure the same concept. They are the same in number, structure and level of
difficulty. An analogy would be using one scale to measure the weight of a subject
today and after one week, using a different scale to measure the weight of the same
subject. The following steps are involved in the equivalent form method.

1). Sample different items from the domain of indicators that measure the variables

2). Divide the items thus sampled into two groups or forms

3). Administer one form to a group of subjects that is randomly selected.

4). Then after a certain period of time, then administer another form of instrument to
the same subjects, keeping all other conditions constant.

5). Correlate the scores obtained from the two forms of the instructions.

If from the above the correlation coefficient is high, the instrument is said to yield data
that have a high equivalent-form reliability. This method estimates the stability of data
as well as the equivalence of the items in the two forms, the major problem in this
technique is the construction of two tests, which measures the same concept, and this
method is difficult and expensive in terms of time and resources. However, the
equivalent-form method is commonly used in establishing the reliability of standardized
test data such as intelligence test, achievements tests etc.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 71 of 98
Split-half technique

This technique of assessing reliability requires only one testing session, in this approach,
an instrument is designed in such a way that there are two parts. Subject’s score from
one part are correlated with scores from second part, the major a advantages of this
method is that it eliminates chance errors due to differing test conditions as in the
testretest or equivalent-form techniques, the following are the steps involved in the
splithalf techniques.

1). Sample items from the domain of indicators that measure the variable.

2). Administer the total test to an appropriate group

3). At random divide the scored items into two groups. Alternatively, one can group up
all the odd-numbered items together and the even ones together as well 4). Compute
each subject’s total score from the two groups of items.

5). Correlate the scores from the two groups of items for all the subjects.

Data with a higher split-half reliability will have a higher correlation coefficient, the fact
that we are correlating half of the test score, that implies that the coefficient so
computed does not represent the reliability of the whole instrument and so the a
correlation factor is therefore applied to the computed coefficient and thus the
adjusted coefficient then represents the reliability of the entire test.

The correction is done using the spearman-brown prophecy formula, it important to


know that there are many ways of dividing the items into two parts and each method
used will result into different correlation coefficients hence different reliability estimates
will be obtained for the same instrument test. Increasing the number of items in the
instruments increases the chances of obtaining a consistent estimate of the reliability
of the data.

The Internal Consistency Technique.

The internal consistency of data is determined from scores obtained from a single test
administered by the researcher to the sample of the objects. In this approach a score
obtained in one item is correlated with scores obtained from other items in the
instruments. Cronbach’s Coefficient Alpha is then computed to determine how items
correlate among themselves. Cronbach’s Alpha is a general form of the
KunderRichardson (K-R)20 Formula.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 72 of 98
The use of K-R 20 formula for assessing internal consistency of an instrument is based on
the Split-Half reliabilities of data from all possible halves of the instrument, the use of this
formula reduces the time required to compute a reliability coefficient in other
methods. Its application also results into a much more conservative estimate of
reliability.

Kr20 = (k)(S2-∑2 s )

(S2)(K-1)

KR20 = Reliability coefficient of internal Consistency.

K= Number of items used to measure the concept

S2= Variance of all scores.

s2= variance of individual items.

A high coefficient implies that items are highly correlated among themselves or there is
consistency among the items in measuring the concept of interest, this is sometimes
referred to as homogeneity of data.

Validity
Validity is the degree to which results obtained from the analysis of the data actually
represent the exact phenomenon. Validity is the accuracy and meaningfulness of
inferences, which are based on the results of the research

Validity therefore has to do with how accurately the data obtained from the study
present variables within the study. If such data is a true reflection of the variables, then
inferences based on such data will be accurate and meaningful.

Please note that validity is largely determined by the presence of or absence of


systematic errors in data. Systematic errors are also referred to as non-random errors
e.g

Recall in reliability we said that data under it are affected by random error and here
we are thus saying that validity is affected by non-random errors, this apparent
contradiction implies that an instrument can yield reliable data that are not necessarily
valid.

There are three types of validity in data:


RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 73 of 98
• Construct validity

• Content validity

• Criterion-related validity.

Some researcher however argue that these are not really types of validity but are
techniques of validating a study.

Construct validity:

Construct validity is the measure of the degree to which data obtained from an
instrument meaningfully and accurately reflects or represents a theoretical concept.

“Construct Validity testifies to how well the results obtained from the use of the
measure fit the theories around which the test was designed.”

Construct Validity is assessed through Convergent or Discriminant Validity.

Convergent Validity: This is established when the scores obtained with two different
instruments measuring the same concept are highly correlated.

Discriminant Validity: This is established when based on theory, two variables are
predicted to be correlated, and the scores obtained by measuring them are indeed
empirically found to be so.

For example, suppose a student scores 95% in research method, would a score of 95%
points in a research methods truly reflect the true ability of the student in research
methods and conducting research?

Assessing the construct validity of data is very difficult a task because it requires a
researcher to establish theoretically derived hypotheses involving the concept under
consideration. For example. Let’s suppose that a researcher wants to study the
motivation of workers in a certain institution. The researcher would have to develop an
instrument to measure the concept “motivation” one could first hypothesize that
motivation in human beings related to other constructs such as ; interest in doing
something, risk attitude, rewards associated with it etc. the researcher would then
develop an instrument based on this hypothesis. The researcher would select a
random sample of workers from the institution and then administer the instrument to
the subjects. At the same time the researcher would try to observe the hypothesized
characteristics in the subject. If persons who score high on motivation instrument did
indeed take more risks, have interest in them and look at rewords involved etc. this
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 74 of 98
would be enough evidence to support the construct validity of data obtained using
this instrument.

In sum, Goodness of measures is established through different kinds of validity and


reliability as depicted in figure 1.1.

Content Validity

This is the measure of the degree to which data collected using a particular instrument
represents a specific domain of indicators or content of a particular concept. In
designing an instrument that will yield content-valid data, the researcher must first
specify the domain of indicators which are relevant to the concept being measured.
Theoretically, a content-valid measure should contain all possible items that should be
used in measuring the concept.

Suppose one is interested in measuring in measuring management skills, then in


principle one should develop a complete specification of the concept “Management
skills” this means identifying all items that ought to be used to measure it, for example
the concept “management skills” might involve such factors like: Decision making,
planning, financing, public relations etc. often times, it is important is impossible to
construct an instrument that includes all the possible items that might be used to
measure a given concept.

To circumvent the above problem, researcher resort to what is called sampling validity:
in this case, a researcher, selects a representative sample of indicators from the
domain of indicators of the concept.

The usual procedure of assessing content Validity of a measure is to use professional or


experts in the particular field. The instrument is given to two groups of experts, one
group is requested to assess what concept the instrument is trying to measure and the
other group is asked to determine whether the set of items or checklist accurately
represents the concept under study (Olive Mugend and Abel Mugenda 2003)

Criterion-Related Validity

Criterion-related validity refers to the use of a measure in assessing subject’s behavior


in specific situations. If an instrument purports to measure performance in a job, the
subjects who score high on the instrument must also perform well their jobs.

There are two types of criterion-related validity are recognized of predictive and
concurrent.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 75 of 98
Predictive Validity: refers to the degree to which obtained data predict future
behavior of subjects.an engineering firm may for example advertise posts of two
graduates in civil engineering. Two hundred graduates may apply for the post and
during the interview, they are given a test, the test scores are supposed to assess the
graduate’s performance on job once they are employed. The extent to which such
measures determine the performance on the job of the selected graduates in future is
the predictive validity of the instrument.

If the data obtained using the tool has predictive validity, the graduates’ score on the
test would correlate highly with a measure of their future performance on job.

Concurrent Validity: this on the other hand refers to the degree to which data are able
to predict the behavior of subjects in the present and not in future. An example of this
may be found in medical studies, psychiatry. A psychiatrist might use a measure to
establish whether a patient is schizophrenic. In this case a patient’s scores on a
psychiatric test would correlate highly with his or her present behavior if the instrument
does indeed yield data that accurately represent this type of mental illness. (Mugenda
and mugenda 2003)

INTERNAL AND EXTERNAL VALIDITY

In reference to the previous chapter discussed in relation to estimating or assessing


various types of validity of data. It was noted that the quality of research study is
affected by the validity of the measurements obtained. There are two more “types” of
validity which are so paramount in research processes, that is internal validity and
external validity of the study.

The Internal validity of a study depends on the degree to which extraneous variables
have been controlled for in the study. If extraneous variables have not been controlled
for, one does not know whether the observed effects of the dependent variables are
due to the independent variables or to extraneous variables. In the situation where the
researcher has controlled for extraneous variables, changes on the variables can
accurately be attributed to the independent variables, in this case the study is said to
have high internal validity.

External validity of the study has to do with representativeness of the sample with
regard to the target population. External validity refers to the degree to which
research findings can be generalized to the populations and the environments outside

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 76 of 98
the experimental setting. The question at hand is “can the same results be obtained at
other times and in other settings.

If the research findings are only applicable to the sample, the study findings are not
externally valid and as such, they are not generalizable to other populations.

Researchers sometimes use the term ecological validity to refer to the extent to which
research findings can be generalized to other environmental settings. High ecological
validity means that the research finding can be generalized to other environmental
setting.

In a nutshell internal and external validity are somewhat inversely related to each
other.

As one strives to balance between internal and external validity, it is important to be


aware of the major factors that might pose threats to both “types” of validities in a
study.

THREATS TO INTERNAL VALIDITY

According to Campbell and Stanley, they identify eight factors that often threaten the
internal validity of a research study. These are:

History:
some research studies, especially in the physical and biological sciences, extend over
a long period of time, during such an extended period, events occurs, which have an
influence on the subject such that final results may be partly due to extraneous factors,
such events or factors, though extraneous to the study, influence the research findings
and hence internal validity of the study is reduced, occurrence of events that
influence experimental units during the course of the study are history.

Maturation:
Maturation Refers to biological or psychological processes which occurs among the
subjects in a relatively short time and which influences research findings. During the
course of the study, subjects may become more intellectually enlightened or
motivated. On the other hand subjects may become fatigued, irritated or
discouraged. An example may be seen in educational studies where a researcher
may want to establish the effectiveness of two teaching methods in improving the
reading skills of students, the students can learn through the actual teaching or they
can learn from their friends who already know. Maturation can be controlled through
application of an appropriate research design.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 77 of 98
Instrumentation:
Instrumentation is a problem when the measuring instrument is unreliable, if the
researcher uses the equivalent form approach in a pretest-post-test situation and both
forms of the test differ on the level on difficult or content. The difference between the
pretest and post – test scores will not solely be due to the treatment but also the
difficulty or ease of the items. Another related problem is evident when several
research assistant are collecting data from the same study. The researcher assistant
may not be consistent among themselves in observing, measuring, scoring or assessing
the characteristics under study. To avoid this problem the researcher should develop
accurate measures or instruments and standardize data collection procedure by
holding a training session for everybody who is involved in the actual data exercise

Pre-Testing:
In social science studies, a pre-test is administered to the subjects followed by
treatment and at the end of the experiment, a post-test is administered to the same
group or subjects. The difference between the post-test scores and the pre-test score is
the measure of the treatment effect. A pre-test however sensitizes subjects and they
tend to perform better in a post-test not because of treatment alone but because
they have been sensitized to the test. Pre-testing in other words is often a common
source of contamination of findings or data in social science research.

Please not that as the period between the post-test and pre-test increases, the treat to
internal validity from this factor is minimized, a reliable method of avoiding this problem
is to use ……………………..technique.

Statistical Regression:
Statistical regression is a problem where the selection of subjects in based on their
performance on the pre-test. Suppose you choose 20 students for an interview for the
post of a project Engineer and the participants are given a pre-test and 10 top are
selected for the position and on completion of the induction programme, the
participants are given a post-test to evaluate their effectiveness for the positions, it’s
very likely that their mean score on the post-test will be lower than their mean score on
the pre-test, On the other hand if the bottom 10 students in the pre-test were selected,
their mean score on the pre-test would be lower than their score on the post test. The
explanation of this phenomenon is based on the fact that extreme scores tend to
have the highest errors of measurement. On re-testing extreme scores tend to regress
towards the mean.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 78 of 98
Attrition
Attrition or experimental mortality refers to a situation where many subjects drop out of
the study before the study is complete, the trend of drop out may be organized such
that only subjects with certain common characteristics are left for study purposes. It
could be those with less or no opportunity to joining another sector (employment
industry) or less motivated or those with low self-esteem etc who drop out leaving the
more motivated and creative subjects. This leads to a biased outcome coz
representativeness is compromised, attrition is usually a problem associated with
studies of long duration especially in physical and biological sciences.

Differential selection.
Differential selection occurs when subjects are systematically selected into a treatment
group, i.e. if a subject is selected for a study because they volunteered, comparing
such a group to a control group of non-volunteers introduces a bias and errors in the
results. The volunteers are likely to be motivated and interested than nonvolunteers,
such factors will confound the results. Differential section is often a factor when a
researcher uses a whole, intact group as a sample. A point in case is studying
productivity of workers in an industry, taking one industry is a differential section and
the data may not really valid. (Mugenda and mugenda 2003)

Selection-Maturation Interaction.
Selection-maturation becomes a problem when a researcher systematically selects
subjects into the treatment groups, which are extremely different on salient
characteristics, let’s say a researcher selects a sample of people who have travelled
widely and another of people who have not travelled outside their country, the two
groups of people will differ in their attitudes and values, comparing the two groups on
measure of attitude would be confounded by errors and the results will just be a
reflection of the initial advantage of the experimental group over the control group.

THREATS TO EXTERNAL VALIDITY IN RESEARCH.

Accessible and target populations


Generalization of research findings largely depends on the degree to which the
sample, accessible population, and the target population are similar on salient
characteristics, it important to note that subjects are sampled from the accessible. If
the sample, the accessible and target population are similar on salient characteristics,
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 79 of 98
then generalization of the research findings can be made to the target population
with confidence.

Control of extraneous Variables


Extraneous variables confound the effects of the independent variables on the
dependent variables. Researchers always control the effects of extraneous variables
by including them in the study. Strict control of these variables increase the internal
validity of the study but may at the same time reduce the generalizability of the results.
The researcher therefore aim at balance between internal validly and generalizability
of the study.

Pro-Test-Treatment Interaction
Take an example of the study that uses a pre-test and a post-test, subjects may score
higher on the post-test because of both the treatment given and the pre-test
sensitization. Pre-test treatment occurs in many studies depending on the level of the
pre-test sensitization present. The pre-test-treatment interaction makes the results only
applicable or generalizable to other groups which have been pre-tested and
therefore results are not generalizable to the target population.

Explicit Description of the Variable


The variables in the study must specifically be defined both conceptually and
operationally. Detailed description of the physical setting, experimenter training,
subject’s instructions, measuring instruments etc ought to be stated.

The above detailed description helps other researchers to replicate the study to
increase the degree to which results are generalizable to other populations, a
researcher must operationalize the variables in such a way that the measures have a
meaning outside the settings of a particular study, conclusions and generalizations
must be made after a careful consideration of the research settings and the
measurement of the variables in the study.

Non-Randomness of the Sample

Selection treatment interaction is often present where samples are not drawn at
random from accessible populations, it may also be present where whole, intact
groups are randomly selected using some form of cluster sampling. Results from studies
which are done with non-random groups can only be generalized to those groups
because of the unrepresentativeness of the sample used.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 80 of 98
Multi-Treatment Interference
Multi-treatment interference occurs when treatments are applied to the same group
but at different times, in this type of study, subjects are given treatment A and the
effects measured, after some times the same subjects are given treatment B and
effects measured. The results from the two treatments are then compared, if the
differences are statistically significant, then one can comfortably conclude that
treatment A is better than treatment B or vice Versa. The problem with this is when
treatment A takes long to wear off such that treatment A continues to influence the
subject even after B is being or has been administered, in the above scenario it
becomes difficulty to determine the true difference between the two treatments.
(What do you think is the solution to be adopted here?)

1) Read and make notes about the common effects that are related to the
research process

2) Read and make notes on the common research paradigms

End of Chapter
Three

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 81 of 98
DATA ANALYSIS AND PRESENTATION

An Overview of Data Analysis

Data obtained from the field in raw form is difficult to interpret, such data must be
cleaned, coded, and key-punched into a computer and analyzed. It’s from the result
of such analysis that researchers are able to make sense of the data.

In this section we shall discuss the process of data coding, data entry and the
common statistical procedures used in data analysis.

Pre-Analysis of Data

Once the questionnaire or other measuring instruments have been administered, the
mass of raw data collected must be systematically organized in a manner that
facilities analysis. If empirical or quantitative analysis is anticipated, the response in the
questionnaire will be assigned numerical valves for example, if the responses
anticipated are yes and No, one would then assign the number 1 to yes and 0 to No
or vice versa, this is much more applicable if questions in a questionnaire are
closedEnded.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 82 of 98
It is important to note that a researcher might include open-ended items for purpose
of obtaining qualitative data or non-empirical data. Analyzing this type of data
requires experience in qualitative data analysis techniques.

Coding and Entering Data

The conversion of data into numerical codes is referred to as coding, to permit


quantitative analysis, data must be converted to numerical codes representing
attributes or measurements of variables.

Coding should include as much information as possible because one the coded data
is entered into the computer, it’s impossible to recover any details. Only one code
should be assigned to each response category.

The coding process starts with preparation of code book, the code book is a
document that describes in specific details the coding scheme to be followed, the
code book describes the code assignment for each response category for each item
in the questionnaire, and you then use the ode book to transfer information to the
code sheet, a code sheet is designed to correspond to the number of columns in the
spreadsheet.

Advanced technology have simplified the process of data coding and data entry, for
experienced researchers the preparation of the code sheets can be skipped and
data entered into the computer direct from the questionnaires.

Two recent developments in data coding and entry have significantly reduced the
amount and time needed to code and enter data, these are:

1). Using Bubbles sheets


2). Using Escapable questionnaires.

A bubble sheet is separate from questionnaire and researcher or subject records the
responses by darkening the appropriate circle using a pencil. Complete bubble sheets
are then directly scanned into the computer spreadsheet. The latest technology is to
use escapable questionnaires subjects’ responses are directly scanned from the
questionnaires into a spreadsheet. If the data is to be analyzed manually, a code
book is still very important because it will contain all the information extracted from the
questionnaires in an organized way. However it’s advisable to use a computer for any
kind of data analysis in order to save time and to increase the accuracy of the results.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 83 of 98
Once the data has been entered into the computer rightfully, the choice of statistical
procedure to use for analysis will depend on:

a) Proposed hypotheses and objectives, for example if it is an exploratory study,


where one is interested in exploring an existing situation, then descriptive
analyses might be adequate and if the hypotheses will be tested, this calls for
the use of inferential statistics.

b) The research design used for example, an experimental design, which thus
compares various groups usually calls for analysis of variance.

c) The type of measurement scale used in the measurement of variables. i.e


variables can be measured using nominal, ordinance, interval or ratio scales
etc.

Qualitative Analysis

Many researchers are not comfortable with qualitative data analysis. Qualitative data
analysis refers to Non-empirical analysis, a researcher may be interested in studying an
area which may not require quantifiable data i.e case studies, content analyses and
historical studies, in such studies, the researcher is interested in analyzing information in
a systematic way in order to come up with a useful conclusions and recommendations
In qualitative studies, researchers’ obtain detailed information about a phenomenon
being studied, and then try to establish patterns, tends and relationships from
information gathered.

Quantitative Analysis

The first step in data analysis is to describe or summarize the data using descriptive
statistics. The purpose of descriptive statistics is to enable the researcher to
meaningfully describe distribution of scores or measurements using a few indices or
statistics.

Main types of descriptive statistics

Measure of central tendency are used to determine the typical or expected score or
measure from a sample of measurement or a group of scores in a study. In the social,
measures of central tendency are used to give expected summary statistics of
variables being studied. There are three main types of commonly used measures of
central tendency. These are the mode, mean and the median.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 84 of 98
The Mode

This is the most common attained measurement or value, it the measurement that
appears most in a particular variable among a sample of subjects.

An example is considering the score below: 4 7 6 8 8 3 5 810 12, the mode is 8 since it’s
the valve that occurs most frequently in the sample.

It’s also important to note the following points on the mode:

1) A set of score may have more than one mode. i.e scores 3 4 4 5 6 7 7 7 8 10 11,
in the above set of scores, there are two modes: 4 and 7, such a set of score is
said to be “Bimodal”

2) The mode tends to be unstable, for example, equal sized samples randomly
selected from the same population are likely to have different modes although
they may be very similar on the characteristics being measured.

3) Its possible for a set of scores or measurements not to have any mode when all
the scores in a group occur with the same frequency, in this case the mode is
not helpful in describing the distribution.

The Median

The median is the 50th percentile in a group of scores. It is the score that divides ranked
scores into two equal parts, such that half of the scores are larger than then median
and the other half are smaller. In a nut shell the median is the point below and above
which 50% of the scores fall.

Example1 what is the median of: 65 85 55 74 95

Example 2 what the median of: 21 23 24 25 27 30

The Mean

The mean is the average of a set of scores or measurements. It is the most frequently
used measure of central tendency, it is calculated by adding up all the scores and
dividing by the total number of scores.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 85 of 98
Measure of variability

Although measure of central tendency is very useful in statistics for describing along of
data, they are not sufficient to describe a distribution of scores in more details,
therefore we need to have a measure of how scores differ among themselves in
magnitude. In short we need to have a standard way of describing variability or
dispersion of scores.

Variability

Variability is the distribution of scores around a particular central score or value. In


statistics, the central score is always the mean of the distribution. Variability therefore is
the dispersion of scores around the mean of the distribution. Consider an example
below

Scores: A 78 78 78 80 82 82 82

B 45 55 70 80 90 100 120

For both the cases above the mean and median is 80 but looking closely at them, it
evident that set A Cluster around the mean closely than set B which is much more
spread out, meaning that there is much more variability.

There are three most commonly used measure of variability: the range, the variance
and the standard deviation

The Range

• This is the difference between the highest and the lowest scores in a distribution.

• A small range signifies that the scores are not spread out and a bigger range
means that scores are spread out

• The advantage of a range is that it gives a quicker rough estimates of variability

• And the main weakness is that it only considers two scores that is the highest and
the lowest scores, it is therefore not sensitive to the total distribution.

The standard deviation and the variance

• Standard deviation is defined as the extent to which scores in a distribution


deviate from their mean or average.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 86 of 98
• Standard deviation therefore involves subtracting the mean from the standard
score to obtain the deviation.

• If we square each deviation, sum the squared deviation the divide this by the
total degree of freedom, we then have a degree of variability called variance,
if the valve is small, it means that the variance is small as hence scores are close
together and vice versa.

• By taking the square root of variance, one obtains the standard deviation, the
bigger the standard deviation, the larger the deviation from the mean denoting
greater variability. S2=∑(X1-X)2

n-1

S2=Sample variance

S= Standard deviation

X1=each value or

score n=Sample Size

N-1= Degree of freedom

GRAPHIC REPRESENTATION OF A FREQUENCY DISTRIBUTION

Graphical representation of data is a valuable supplement to statistical analysis. The


graph enables the reader to see the trend of the distribution more easily than simply
looking at numbers in a frequency distribution.

A group should be well labelled on both the vertical and horizontal axes, vertical axis
representing frequencies and horizontal scores.

There are three main graphs that are used to represent data in research reports,
namely:

1). Histograms,

2) Frequency polygons, and

3).Bar charts, pie charts may be used but mostly in engineering or scientific projects.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 87 of 98
Consider data of your own and construct Histogram, Frequency polygons, and Bar
charts

4).Percentages

A percentage is defined as the proportion of a sub-group to the total group or a


sample and ranges from 0% to 100%
Passing grades Frequency Percentages frequency

Vice chancellors list 30 25.0

Dean’s List 60 50.0

Normal progress 20 16.7

Probation progress 10 8.3

Grand total N=100 100%

Percentages are extremely important, especially if there is a need to compare groups


that differ in size, computer aided programmes will compute for you the mean,
standard deviation, percentages etc and thus saving time especially on bigger
samples.

5). Relationships

The last group of descriptive statistics are those that give a measure of relationship
between two or more variables for example one may be interested in measuring if the
level of one’s IQ is equivalent to his/her performance, in the above example a
correlation coefficient would be the best method if both variables are to be
measured.

Other statistics that can be used to measure whether relationships exist among
variables are: chi-square statistics and regression coefficient.

Inferential statistics

The ultimate purpose of research is to be able to generalize the results from samples to
the populations. We use hypothesis testing techniques to generalize findings from the
sample to the population, these techniques are referred to as inferential statistics.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 88 of 98
CHOICE OF TEST OF HYPOTHESIS

They are various types of statistical procedure that are used in testing hypotheses and
the choice of the procedures to use depends on the factors as:

Size of the sample

In testing hypotheses, some data analyses procedures cannot be used if the sample is
too small, for example regression

Types of Variables and Measurement Scale

The type of data analyses procedures used sometimes depends on whether the
variables are continuous or discrete similarly measurement scale (ratio, interval, and
ordinal, nominal) will determine the procedure one should use to analyze data.

Types of research designs

Statistical data analysis procedures also differ depending on the research design used
in the study for example data from an experimental study that compares differences
between two or more groups is best analyzed using analysis of ANOVA). Relationships
and predictions among variables are best determined using correlation and regression
techniques.

Statistical Procedure Used In Inferential Statistics

There are many statistical techniques used in testing hypotheses, in this case we shall
limit ourselves to common few ones, these techniques are categorized as parametric
and non-parametric techniques, in parametric techniques certain assumptions are
made about data and in non-parametric techniques no assumptions are made about
data. Parametric techniques are more powerful than non-parametric techniques
when making inferences.

CORRELATION

The correlation technique is used to analyze the degree of relationship between two
variables, there are various correction techniques that are used normally and the
choice of each technique depends on:

1). whether the variables are continues or discrete

2). whether the scale of measurement used is nominal, ordinal, interval or ratio.
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 89 of 98
The Importance of Coefficient

The correlation analysis explains in details how the variables within the study are
related.

It determines the strength and directions of the association between two variables, this
Is very key because this piece of information forms the basis selecting variables for
further analysis e.g regression analysis.

Test of the Significance of Correlation Coefficient

• We can make inferences using correlational analysis

• Researchers always use significance level of 0.05 or 0.01 although other levels of
significance can be used.

• A significance level is the probability of obtaining similar results through chance.


In other wards if we repeated the study may times using different but equal
ramdom samples, we would obtain a correction coefficient of about 0.70 ninety
five percent of the time. If our level of significance is 0.05.

THE CHI-SQUARE TEST

Chi-square (x2) is a statistical technique which attempts to establish relationship


between the two variables both of which are categorical in nature.

We may want to test the hypothesis that there is a relationship between gender and
number of 1st class degrees in kyambogo department of civil and building
engineering.

The variable gender is categorized as Male and female and variable number of
accidents is categorized as “none”, “few”, “and many”

The chi-square technique is therefore a form of counting the occurrence in the two
variables or more mutually exclusive categories.

The techniques therefore compares the proportion observed in each category with
what would be expected under the assumption of independence between the two
variables. If the observed frequency greatly departs from what is expected, then we
reject the null-hypotheses that the variables are independent of each other. We
would then conclude that one variable is related to the other.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 90 of 98
As already stated that a significance level can be set at 0.05 or 0.01, the chi-square
technique yields on value which should be equal or greater than zero, to determine
the significance of our test, we compare the obtained chi-square value with critical or
tabled value. If the obtained value is greater than the critical value, we reject the
nullhypothesis.

Regression

Regression analysis is used when the researcher is interested in finding out whether an
independent variable predicts a given dependent variable, regression may be
categorized under: simple and multiple regression.

Simple regression is used when a researcher is only dealing with only one independent
variable and one dependent variable.

Multiple regression attempts to determine whether a group of variables together


predict a given dependent variable. For example a researcher may be interested in
finding out whether age, education, household size and marital status influence
financial status of a household.

Regression model

A typical regression model is of the form Y=B0+B1X1+£

Where B0= is the constant or the intercept


B1=Slope or change in Y given one unit change in X1
Y=Dependent variable
X1=independent variable
£=Error

Regression analysis also yields a statistic called coefficient of determination or R 2, the


R2 refers to the amount of variation explained by the independent variables, suppose
you compute your R2 to be 0.48, this means that 48% of the variation in a given
dependent variable is explained or predicted by the variable in the equation and the
rest 52% cannot be explained by the variables in the equation.

ASSUMPTION OF REGRESSION ANALYSIS

Regression analysis assumes that:

Each independent variable is linearly related to the dependent variable.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 91 of 98
The observations are independent of each other, which implies that the sample was
drawn at random.

Homogeneity of variance exists i.e. at each level X, the variance of Y value is constant.

Y values are normally distributed around the mean at the level X in the population.

THE ANALYSIS OF THE VARIANCE (ANOVA)

Analysis of variance is a data analysis procedure that is used to determine whether


there are significant differences between two or more groups or samples at a selected
probability level. The key question in to be answered by the analysis of variance are:
what is the probability that the variation among a group of sample means has
occurred as a result of the randomly selecting the samples from the population? Are
the difference among the groups are due to the treatments given or to the chances.

One Way Analysis of Variance

This refers to analysis of variance where groups are being compared on only one
variable but at different levels in other words there is only one independent that is
being measured at either nominal or ordinal levels.

Two Way Analysis of Variance

Often researchers are interested in comparing two or more groups in more than one
variable. For example mean scores of male and females and also performance of
different schools could be included in the same study.

T-test

A t-test is a special case of the Anova. It’s used to test whether there are significant
differences between two means derived from two samples or groups at a specified
probability level. For example a researcher might want to compare IQ performance
from private and public schools. A researcher then gets a sample of 30 subjects from a
private school and another 30 from a public school, and then he/she administers an IQ
test to both groups. A T-test is then used to compare the mean scores obtained by
these two groups. The assumptions discussed under ANOVA also holds for a T-test.
There are two types of T-test;

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 92 of 98
I) THE TEST FOR INDEPENDENT SAMPLES

Independent samples are samples that are randomly formed, that is formed without
matching. In such samples, the members of one group are not related to members of
the other group in any systematic way other than that they are selected from the
same population. It’s assumed that the two groups are the same on the measure of
interest at the beginning of the study. If they are different at the end of the study, then
the treatment administer to the groups made them different. To determine whether
there is a significant difference between the means of the two independent samples,
a T-test is used.

ii) The T-test for non-independent samples

Non-independent samples refers to samples that are formed by some types of


matching for example; if the same group is pretested on the some dependent
variable and post-tested at a later date, the samples are non- independent and
scores on the dependent variable are expected to be correlated. A special T-test for
correlated or non - independent samples must be used to determine whether there is
significant difference between the means of the two samples or between the means
for one sample at two different times.

ETHICAL ISSUES IN RELATED TO RESEARCH

1) Ethical issues relating to individual researcher

Since researchers are people genuinely concerned about people’s quality of life, they
must be people of intergrity who will not undertake research for personal gains or
research that will have negative effects on others. There are laws which prohibit
unethical behavior and researchers could be faced with humiliating situations if such
laws are ignored.

2) Research plagiarism

Plagiarism refers to situations where a researcher refers to another person’s work as


theirs without acknowledging the owner, stealing ideas from another scholar etc.
plagiarism is a crime that’s punishable by law and therefore it’s unethical to use
another person’s work without acknowledging the source.

3) Misuse of Privileges

A researcher has some powers over the subjects owing to the training they have, their
expertise, their legal authority to undertake research and their perceived ability to
RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 93 of 98
provide help especially in Africa where poverty levels is very high. Research subjects
therefore participate in research on a basis of trust, it would be extremely unethical for
researchers to abuse this trust by using their powers negatively. For example it will be
unethical for a doctor researcher to undertake certain research tests on the pretext of
providing treatment and above all it’s unethical for a researcher to use the data
collected to get somebody in trouble or to stigmatize them.

4) Confidentiality and Privacy

Respondents should be protected by keeping the information given confidential,


especially if confidentiality has been promised, in some cases the respondents may
not be that concerned about confidentiality but their consent must be thought before
revealing any information. Lack of confidentiality and mishandling information
provided may cause respondents physical or psychological harm

5) Anonymity

Anonymity refers to the identity of an individual being protected either by using


numbers, third parties or pseudo names, a researcher could disclose information about
a particular individual but protect the identity and privacy of that person. Anonymity
therefore refers to situation where respondent’s name is not disclosed. Sometimes its
not always necessary to keep names anonymous in the interest of follow up efforts
especially in longitudinal studies. On the other side, it is important to always keep
anonymity if sensitive issues are involved in the research.

6) Physical and psychological Harm

A researcher should never undertake a research that may cause physical or


psychological harm. A researcher should do all the preliminary tests and obtain all the
background information in an effort to avoid imparting any harm to subjects, in social
research psychological harm is more likely to occur than physical harm. Psychological
harm can be caused by asking embarrassing questions, expressing shock or using
threating statements or compelling people to say something that they don’t believe in
or causing fear and anxiety among respondents.

7).Voluntary and informed consent.

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 94 of 98
A researcher must confirm to the principle of voluntary consent where the respondents
willingly participate in a research process. It’s unethical if the researcher failed to
disclosure the real purpose of the research in fear of the respondent’s refusal to
participate. In line with the above, subjects must be told the truth and be given all the
facts relating to the research in order to make an informed decision to participate or
not to participate in the exercise.

8). Use of vulnerable or special population in your study

It is considered unethical if populations which are disadvantaged in one way or the


other is used in a study without their consent or consent of the guardian. Examples of
these groups include: children, sick people, the poor, and others with special needs,
permission from those people or their caretakers must be sought and must be based
on informed consent before beings included in the study.

9). Dissemination of Findings

It’s unethical to conceal research findings after completion of research. Some


researchers may decide not to reveal the findings if they are contrary to their
expectations, or their sponsor’s expectations, a researcher for example may fail to
disclose the findings of a certain research if they are to affect a policy negatively and
yet there are some minority group that benefit from such polices, this is wrong and not
allowed in research.

Other ethical issues are related to publication of research findings, every researcher
should be aware of intellectual property rights, for example if a research was done as
a team, then it would be very wrong for participant then to publish a book or findings
as his/her own.

10). Academic Freedom.

Academic freedom is the existence of an open and unrestricted atmosphere in


exchanging ideas and information. Academic freedom is very key in research
because researchers must be free to discuss and publish findings without fear of
intimidation, losing a job or being victimized. 11) Ignoring pertinent issues in research

12). Ethical issues in experimental designs

13). Use of test in research

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 95 of 98
LOGISTICAL ISSUES RELATED TO RESEARCH

Conducting research is a process that requires careful planning, this is very necessary
considering the fact that research is very expensive a process to undertake in terms of
time, financial and human resources.

A point in case is suppose all the data that are collected from the field are found to be
wrong or unaccepted or lost, replacing such data would be almost impossible

Apart from enhancing reliability and validity of data, careful planning before starting a
research process is very key and also minimizes problems often encountered by the
researcher in the field during the exercise.

Logistics in research refers to all those process, activities, or actions that a researcher
must address or carry out to ensure successful completion of the research project. The
logistics of conducting research can be divided into three categories namely: Pre-field
work logistics, field work logistics and post-field work logistics.

1). Differeciate between research proposal and project proposal (4 marks)


RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 96 of 98
2). There are main sections of a proposal which are considered mandatory and which
must be included in a proposal regardless of one’s disciple.

Briefly explain these main sections of a proposal pointing out key contents in them. (10
marks)

RESEARCH METHODS LECTURE NOTES FOR YEAR III: BY JAMES KAZUNGU ALUKO (ENG),
PGD in project Planning and Management, Bachelor’s Degree in Civil and Building and Diploma in Civil
and Building Engineering Email:[email protected]. 0772 670685
Page 97 of 98

You might also like