GMS 2014 Module 1
GMS 2014 Module 1
GMS 2014 Module 1
MODULE 1.
INTRODUCTION
The main purpose of this module is to introduce you to research and proposal writing. In
order to effectively handle this task, the module has been divided into seven units. Unit one is an
introduction to research. Unit two discusses the scientific context of survey research. Unit three
focuses on how to formulate research problems. Unit four discusses research design. Unit five
looks at constructing instruments for data collection. Unit six is focuses on sampling. Unit seven
is the last unit in this module, it presents the format for the GMS 2014 research proposal and
gives guidance on how to a write a research proposal.
The aim of this module is to introduce you to research methods and techniques. It will
also expose you to various methods and techniques involved in survey research.
TIMES REQUIRED
It will take you approximately three months to undertake the requirements of this
module. The time should be spent on studying the module, reading recommended material, doing
self-help questions and writing the research proposal.
1
STUDY SKILLS
As a distance student, your study skills will be different from students that are resident
at the university. In your case, you will choose what to study, when to study and where to study
from on your own. You will also need to fit your study activities around other professional
and/or domestic responsilities. It is therefore important for you to allocate enough time to your
studies and secure a conducive place to study from.
NEED HELP
In cases where you need help, you should contact the Director, Institute of
Distance Education, University of Zambia, P.O Box 32379, Lusaka. Cell 0978 772259 or 0979
772248, Email: [email protected]
ASSESSMENTS
The assessments under this module are in two categories. These are Continuous
Assessment (CA) and the Final Examination as shown below.
ASSESSMENT
Continuous Assessment: 50%
Broken down as follows:
a) Test 1 10%
b) Test 2 10%
c) Proposal 15%
d) Research Report 15%
2
Final Examination: 50
1.0 Introduction
This unit gives an Introduction to Research. The unit begins with discussing the meaning of
the term ‘Research’ and thereafter discusses the characteristics of research. We will then
examine different types of research from the perspectives of (i) application of the research study,
(ii) objectives of the research and (iii) inquiry mode. In the last part of this unit, we shall discuss
the applications of research.
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Grinnel, R. (1995), Research and Evaluation, Illinois: Peacock Publishers
3
5.0 Time Required
It will take you approximately one hour thirty minutes to work through this unit.
The word research consists of two syllables, re and search. ‘Re’ means again and ‘search’
means to examine closely and carefully. Research can hence be defined as a systematic
investigation to generate new knowledge or solve a problem. By systematic investigation, it
implies that research follows a structured inquiry that utilizes acceptable scientific
methodologies to establish facts. The new knowledge generated through research may help in
describing, predicting, understanding and explaining social and natural phenomena.
Grinnel (1995) defines research as a structured inquiry that utilizes acceptable scientific
methodologies to solve problems and create new knowledge that is generally acceptable. Burn
(1994) states that, research is a systematic investigation to find an answer to a problem. On the
basis of these definitions, we can conclude that research is an organized inquiry designed and
carried out to provide information. Through research, we are able to discover new information to
expand on existing knowledge. Sometimes we may think we already know the answer to our
question or may think the answer is obvious. But until we have subjected our problem to
rigorous scientific scrutiny our knowledge remains little more than guess work or at least
intuition, (Ibid).
From the above definitions, it is clear that research is a process of collecting, analyzing and
interpreting information to answer questions. However, to qualify as research, the process must
have certain characteristics: it must as far as possible, be controlled, rigorous, systematic, valid
and verifiable, empirical and critical.
4
1. Controlled. In real life there are many factors that affect an outcome. A particular event
is seldom the consequence of a one to one relationship; most outcomes are caused by a
multiplicity of relationships and interacting factors. In the study of cause and effect, it is
important to be able to link the effect (s) with the cause (s) and vice versa. In the study of
causation, the establishment of this link is essential; however, in practice, particularly in
social sciences, it is often difficult to make this link. The concept of control implies that
in explaining causality in relation to two variables, you should set up your study in a way
that minimizes the effects of other factors affecting the relationship. This can be achieved
to a large extent in the physical sciences as most of the research is done in the laboratory.
However, in social sciences like Public Administration and Political Science, it is
extremely difficult as research is carried out on issues relating to human beings living in
society where such controls are impossible. Therefore, in social sciences, as you cannot
control external factors, you attempt to quantify their impact.
2. Rigorous. Research requires strictness in ensuring that the procedures followed to find
answers to questions are relevant, appropriate and justified. Again the degree of rigor
varies markedly between physical and social sciences and within the social sciences.
3. Systematic. This implies that the procedures adopted to undertake an investigation follow
a logical sequence. The different steps cannot be taken in a haphazard way, some
procedures must follow others.
4. Valid and Verifiable. This implies that whatever you conclude on the basis of your
research findings is correct and can be verified by you and other.
5. Empirical. This means that any conclusions drawn are based upon hard evidence
gathered from information collected from real life experiences or observations.
6. Critical. Critical scrutiny of procedure used and methods employed is crucial to a
research inquiry. The process of investigation must be clear and free from any
drawbacks. The process adopted and the procedures used must be able to stand critical
scrutiny.
Research can be classified from three perspectives namely: application of the research study;
objectives of the research; and inquiry mode employed.
5
1. Application. When you examine a research endeavour from the perspective of its
application, there are two broad categories: pure research and applied research
a. Pure Research. Pure research is concerned with the production of new knowledge and not
the application of its outcomes. It is intended to acquire knowledge for its own sake. An
example of this could be dissertations and theses which students submit as partial
fulfillment of their study program. Other examples of pure research include developing a
sampling technique that can be applied to a particular situation, developing a
methodology to assess the validity of a procedure, developing a theory or framework that
can be used in research, developing an instrument to measure stress levels in people and
finding the best way to measure people’s attitude. Pure research fulfills the academic
objective of research, which relates to the generation of new knowledge.
b. Applied Research. This is the kind of research that places emphasis on application of
knowledge acquired and problem solving. Most of the researches in social and physical
sciences are applied; they are aimed at finding solutions to problems. Applied research
fulfils the utility objective of research which relates to problem solving or policy
formulation.
2. Objectives. When you examine a research from the perspective of its objectives, a
research endeavour can be broadly classified as descriptive, correlational, explanatory
and exploratory.
a. Descriptive Research. A descriptive research attempts to describe systematically a
situation, problem, phenomenon, service or program or provide information about, say,
the living condition of a community, or describe attitudes towards an issue. For example,
it may try to describe the type of services provided by an organization, the administrative
structure of an organization, the attitudes of workers towards management, strategies put
in place by an organization to improve productivity and citizens’ perceptions towards
politics. The main purpose of such studies is to describe what is prevalent with respect to
the issue or problem under consideration.
b. Correlational Research. The main emphasis of this type of research is to establish or
explore the existence of a relationship, interdependence or association between two or
more aspects of a situation. What is the impact of advertising on the sale of a product?
What is the relationship between technology and unemployment? What is the
6
relationship between education and voting in an election? What is the relationship
between income and job satisfaction? What is the impact of incentives on productivity of
workers? These studies examine whether there is a relationship between two or more
aspects of a situation or phenomenon and are therefore called correlational studies.
c. Explanatory Research. This type of research attempts to explain why and how there is a
relationship between two aspects of a situation or phenomenon. This type of research
attempts to explain, for example, how does the home environment effects children’s level
of academic performance? Why does political violence lead to lack of interest in politics?
Why do some people have a positive attitude towards an issue while others do not
d. Exploratory Research. This is when a study is undertake with the objective of either to
explore an area where little is known or to investigate the opportunity of undertaking a
particular research study. When a study is carried out to determine its feasibility, it is
called a feasibility study or a pilot study. It is usually carried out when a researcher wants
to explore areas about which he/she has little or no knowledge. A small scale study is
undertaken to determine if it is worth carrying out a detailed investigation.
Although, theoretically, a research study can be classified in one of the above perspectives, in
practice, most of the studies are a combination of the first three.
3. Inquiry Mode. When you examine a research from the inquiry mode perspective, you
look at the process adopted to find answers to research questions. Broadly, there are two
approached to the inquiry mode; the structured approach (quantitative research) and the
unstructured approach (qualitative research)
a. The structured Approach / Quantitative Research. The structured approach to inquiry is
usually classified as quantitative research. In the structured approach everything that
forms the research process – objectives, design, sample and questions that you plan to ask
are pre-determined. The structured approach is more appropriate to determine the extent
of a problem, issue or phenomenon. A study classified as quantitative is primarily
concerned with the quantification of a problem, situation or phenomenon. Examples of
quantitative research are census, labour force surveys, health surveys, election opinion
polls and others. Quantitative research tries to answer questions like how many, how
often and how much.
7
b. The Unstructured Approach / Qualitative Research. The unstructured approach to inquiry
is usually classified as qualitative research. This approach allows for flexibility in the
research process such as the research design, sample size and the questions that you
formulate to ask your respondents. The unstructured inquiry is more appropriate in
exploring the nature of a problem, issue or phenomenon. A study is classified as
qualitative if its purpose is to describe a situation, phenomenon, problem or event. The
description of an observed situation, the historical enumeration of events, an account of
different opinions people have about an issue and a description of living conditions of
people are examples of qualitative research. Qualitative research tries to answer questions
like who, why, where, when and how.
8
7.0 Summary
You have been informed in this unit that research is a systematic investigation to
generate new knowledge or solve a problem. By systematic investigation, we mean that research
follows a structured inquiry that utilizes acceptable scientific methodologies to establish facts.
This, therefore, suggests to you that for an undertaking to qualify as research, it must use
scientifically acceptable methodologies. The unit has also showcased a number of characteristics
of research besides exposing you the different types of research and the applications or uses of
research.
After reading through unit one, you should answer the questions below. It is important
for you to attempt the questions in order to gauge how much you have comprehended the
material presented in this unit. If you are having challenges in answering the question, read unit
one again.
9
UNIT TWO: SCIENTIFIC CONTEXT OF SURVEY RESEARCH
1.0 Introduction
This unit discusses the scientific context of survey research. The unit begins by explaining
various sources of knowledge and shows why science is the mode used to generate knowledge in
academic fields of study. We will then distinguish between social sciences and natural sciences
and classify survey research as a method of social science. Thereafter, we shall look at the goals
and aims of social sciences and conclude by examining the steps in the research process.
The aim of this unit is classify survey research as a scientific method of generating knowledge.
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Nachimias, D. and Nachimias, D. (1996), Research Methods in Social Sciences, 5th Ed,
London: St. Martin Press
McNabb, D. (2009), Research Methods for Political Science: Quantitative and
Qualitative Methods, New Delhi: PHI Learning Private Limited
10
5.0 Time Required
It will take you approximately four hours to work through this unit.
In our daily lives we know things in different ways. We know that water boils at 100 degrees
Celsius, that the HIV virus causes AIDS, that Democracy is better than Dictatorship, that lack of
motivation affects workers productivity. In some cases we know something because we believe
what we read in the media or hear on the radio. In some cases, we know something through
personal experience or because it is consistent with common sense or what someone we view as
reliable has told us. Besides what has been mentioned, there are various ways of knowing things
such as through:
1. Intuition – this is a way of knowing things through gut feelings. It is subjective and
based on personal feelings rather than on fact or proof.
2. Habit – this involves believing what we do because it is a tradition to do so.
Traditions include opinions, beliefs, practices and customs which are passed on from
generation to generation.
3. Mystical – this where knowledge is assumed to be solicited from divine and
supernatural powers. It is acquired from the divine and other spiritually endowed
individual such as prophets or witch finders.
4. Authoritarian – this where it is assumed that knowledge is derived from individuals
who are politically and socially producers of knowledge.
5. Rationalistic Mode - this is where knowledge is acquired through judgment based on
careful thought or reasoning.
However, the above sources of knowledge have weaknesses which science is able to address.
11
6. Science. Science is a way of generating knowledge which is obtained through the use
of scientific process. This way of knowing differs from information derived from
myth, intuition, beliefs, casual observation and common sense. It has certain
characteristics that these other types of knowledge do not have. Scientists believe that
their findings are based on systematic observations and that their claims can and must
in principal be verified or falsified by a shared set of standards and procedures. For
knowledge (information) to be considered scientific, it must exhibit several
characteristics:
a. Empirical – this means knowledge must be based on hard evidence from real life
experiences. It must be proven to be true by means of objective observation.
Empirical means relying or based on observation or experience. In science, what is
factual information or knowledge is what you are able to prove.
b. Verifiable – this means that whatever you conclude on the basis of your findings must
be proved by others. Acceptance or rejection of a statement regarding something
known must be influenced by observations.
c. Systematic – Knowledge must be generated by following an acceptable logical
sequence. The different steps cannot be undertaken in a haphazard manner.
d. Logical – knowledge must be logical insofar as it is derived from deductive and
inductive reasoning. Deductive reasoning is reasoning from the general to the
specific, such as using theory to explain a specific event. Inductive reasoning is
reasoning from the specific to the general such as making a generalization based on
one’s observation.
e. Replicable – if someone uses science to generate knowledge, another person who
uses the same methods in similar circumstances should come up with the same
results.
12
differences in the subject matter on which scientific knowledge is generated, we have two
distinct branches of science namely; social sciences and natural sciences.
The similarities between these two sciences are that they both use scientific methods to
generate knowledge such as through research and observations. Both sciences aim at describing,
predicting, explaining and understanding certain phenomenon. Both sciences have similar
characteristics. For example, physics has universal law like the law of gravity, when you throw
an object up anywhere on earth, it will come down. In Public Administration, there are also
principals which are applied universally like the hierarch of authority. Similarly, we are able to
predict the out an event in chemistry such as combing two atoms of hydrogen and one atom
oxygen which give us water. In political science we are able to predict what happens when a
government losses legitimacy. Both social and natural sciences use research studies in order to
generate knowledge.
However, the differences between social and natural sciences are that social sciences like
Public Administration and Political Science are concerned with the study of society. Political
scientists use scientific methods to generate knowledge about power relations in society. On the
other hand, natural sciences study natural phenomenon in the physical environment such as
Geography, Physics, Chemistry and Biology. Social sciences deal with human beings; this means
that there is a presence of normative values. Normative values are feeling, beliefs and customs
which compromise objectivity when conducting research in society. On the contrary, natural
sciences are not affected by normative values because of their subject matter.
In social sciences like Public Administration and Political Science, survey research is used as
way of generating scientific information. A survey research involves a systematic collection of
data from a sample of individuals, thereafter the information is analyzed and interpreted in order
to arrive at a conclusion. Through the use of survey research, social scientists are able to generate
information which satisfies the requirements of science by;
13
2. Generating knowledge derived from reality that is from observations, perceptions or
experiences of what actually exists.
3. Generating information which can be reproduced by other researchers conducting the
same research in similar situations.
4. Generating information which can be transmitted to other contexts.
6.4 Goals and aims of Public Administration and Political Science as Social Sciences
The aim and goals of Public Administration and Political Science as social sciences are;
The research process is an outline of steps which one has to undertake when conducting
research. It is synonymous with research methodology. The research process aim to familiarize
you with the steps and procedures involved at each step when conducting research. Suppose you
want to go for a drive, you must first decide where you want to go and which route to take. If
you know the route, you do not need to consult, but if you do not, you need to consult someone.
As with your drive, there are two important decisions to make with your research journey. The
first is to decide what you want to find out about, or what research question (s) you want to find
out about (the research problem you want to answer). Having decided upon your research
questions or problems, you then need to think of how to go about finding answers. The path to
finding answers to your research questions constitutes research methodology. At each
operational step in the research process, you are required to choose from a number of methods,
procedures and models of research methodology which will help you best achieve your
14
objectives. The steps presented herein are not absolute as there are a number of variations which
could be made.
1. Step I: Formulating a research problem. This is the first and most important step in
the research process. A research problem identifies your destination, it tells others
what you intend to research. The more specific you are the better as everything which
follows is influenced by the way you formulate your research problem.
2. Step II: Conceptualizing a research design. This is an extremely important feature of
research. The main function of research design is to explain how you will find
answers to your research questions. The research design sets out the logic of your
inquiry. A faulty research design results in misleading findings. Therefore, research
design is crucial to arriving at valid conclusions.
3. Step III: Constructing instruments for data collection. Anything that becomes a tool
for collecting information for your study is called a research tool or a research
instrument. For example, questionnaires, interview guides and observation forms are
all classified as research tools.
4. Step IV: Selecting a sample. The accuracy of your findings largely depends on how
you select your sample. The basic objective of any sampling design is to minimize the
gap between the value of a sample and those of the population. There are different
sampling strategies which are used in research. You need to be acquainted with
sampling designs to select the one most appropriate for your study.
5. Step V: Writing a research proposal. A research proposal is an overall plan which
tells a reader about one’s research problem and how one intends to investigate it. A
research proposal must tell a reader about what you are proposing to do, how you
plan to do it and why you selected a proposed strategy. The format for research
proposals differs from one discipline to another, it is vital that as you develop your
proposals in PAS 2014 you follow the format which has been given in unit seven of
this module.
6. Step VI: Data collection: Having formulated a research problem, developed a study
design, constructed research instruments and decided on the sample, you then collect
15
data from which you will draw conclusions and inferences for your study. Depending
on the plan for data collection you have indicated in your research design, you may
commence interviews, making observations, administering questionnaires and others.
7. Step VII: Data analysis / processing: Data analysis entails turning raw data you have
collected at the preceding stage in to meaningful information. You have to consider
whether data will be analyzed manually or using a computer and whether the data you
are dealing with is qualitative or quantitative. If your study is purely qualitative, you
can write your report based on your field notes from interviews, observations or
reviewing of documents by manually analyzing the contents of your notes (contents
analysis) or by using computer software NVIVO or Ethnograph. If you are using
quantitative data analysis, it is necessary to decide upon the type of analysis required
such as frequency distributions, cross tabulation, chi-square, regression, correlation
and other statistical analysis.
8. Step VIII: Writing a research report: This is the last step in the research process. The
report informs your readers what you have done, what you have discovered and what
conclusions you have drawn from your findings. Just as in the case of the format for a
research proposal, there are numerous ways in which you can write a research report.
It is therefore imperative that when you will be writing your research report for PAS
2014, you strictly adhere to the format which has been given in unit 11 of PAS 2014
module 2.
The eight steps presented above cover the total spectrum of a research endeavor, starting
from problem formulation to writing a research report. Subsequent sections will focus on
discussing these steps in detail as well as discussing the concepts which will arise at each stage.
7.0 Summary
You have been informed in this unit that science is a way of generating knowledge
based on evidence from real life experiences. Scientific knowledge is distinguished from other
sources of knowledge because it is based on empirical evidence. Survey research is used as a
way of generating scientific knowledge in academic fields of study. This is because the
methodologies used survey research satisfies the requirements of science. Furthermore, the
16
research process, which is an outline of steps one has to follow when conducting research, has
eight (8) steps. These steps should be followed systematically when undertaking research.
After reading through unit two, you should answer the question below. It is important
for you to attempt the question in order to gauge how much you have comprehended the material
presented in this unit. If you are having challenges in answering the question, read unit two
again.
17
UNIT THREE: FORMULATING A RESEARCH PROBLEM, IDENTIFYING
VARIABLES AND CONSTRUCTING HYPOTHESIS
1.0 Introduction
This unit discusses how to formulate a research problem, identifying variables and
constructing hypotheses. It begins by defining a research problem and explaining various aspects
of a research problem. Thereafter, we shall focus on identifying and categorising variables. We
will then look how to construct hypotheses.
The aim of this unit is to discuss the formulation of a research problem, identification of
research variables and construction of hypotheses.
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Nachimias, D. and Nachimias, D. (1996), Research Methods in Social Sciences, 5th Ed,
London: St. Martin Press
18
5.0 Time Required
It will take you approximately four hours to work through this unit.
A research problem is an idea or issue which becomes the basis of your inquiry,
investigation or research. However, you should make sure that your idea or issue is researchable
as not all problems lend themselves to research methodology. Broadly speaking, any question
that you want answered or any situation or phenomenon that you want to investigate can become
a research problem or topic for your study.
The formulation of a research problem is the first and most important step in the research
process. It is like identifying your destination before undertaking a journey. The research
problem is like the foundation of a building, the type and design of the building depends upon its
foundation. If the foundation is well designed and strong you expect the building to be also. The
research problem serves as the foundation of a research study. If it is well formulated, you can
expect a good study to follow. The way you formulate a research problem determines almost
every step that follows: the type of study design that can be used; the type of sampling strategy
that can be employed; the research instruments that can be used or developed and; the type of
analysis that can be undertaken.
Most research problems in Public Administration and Political Science revolve around four
Ps:
People;
Problems;
19
Programs;
Phenomena;
The emphasis on a particular P may vary from study to study but generally most studies are
based upon at least a combination of two Ps. You may select a group of individuals (a group or
community as such – people), either to establish the existence of certain issues or problems
relating to their lives, to ascertain their knowledge, attitudes or perceptions towards an issue
(problem), to establish the existence of a phenomenon or to establish the effectiveness of an
intervention (program). Your focus may be upon the study of an issue, an association or
phenomenon. Similarly, you can study different aspects of a program: its effectiveness; its
relevance; its impact; and so on. In order to ascertain these, you collect information from people.
The people provide you with the study population, where as the three Ps furnish the subject area.
Your study population - individuals, groups and communities - are the people from whom
information is collected. Your study area is a problem, program or phenomenon about which the
information is collected. Every research has two aspects, the study population and the subject
area.
When selecting a research problem or topic, there are a number of considerations to keep in
mind. These help to ensure that your study will be manageable and you remain motivated. These
considerations are; interest, magnitude, measurement of concepts, level of expertise, relevance,
availability of data and ethical issues.
20
research problem or topic should be anchored on situations, problems or phenomena
which are relevant to your field.
3. Magnitude – the research problem or topic should be narrowed down to something
manageable, specific and clear. It is extremely important to select a topic that you can
manage within the given time and resources. Even if you are undertaking a descriptive
study, you need to carefully consider its magnitude.
4. Measurement of concepts – if you are using a concept in your study, make sure you are
clear about its indicators and their measurement. For example, if you want to measure the
effectiveness of the Free Basic Education Policy in Gwembe, you must be clear as to
what determines effectiveness and how it will be measured. As you develop your
research, you should be cognizant of the fact that you need to come up with a
measurement of your concept.
5. Level of expertise – make sure you have some elementary knowledge about the task you
are proposing. Although you are learning research and can receive help from others,
remember you need to do most of the work yourself. It is therefore imperative that you
read sufficiently so that you do not experience major challenges.
6. Availability of data – If your topic entails collecting data from secondary sources (office
records, national documents, progress reports, census data and other publications), before
finalizing the proposal, make sure these data are available and in the format you want
them.
7. Ethical issues – another consideration in the formation of a research problem are the
ethics involved. In the course of conducting a research study, the study population may
be adversely affected by some of the questions (directly or indirectly); expected to share
sensitive or private information or expected to be used experimental objects. How ethical
issues can affect a research problem and how they can be overcome should be thoroughly
examined at the problem formulation stage.
If you do not know what specific research topic, issue or idea you want to research on,
you can go through the following:
21
Step 1. Identify a broad field or subject areas that interest you. What problem, situation or
phenomenon in Public Administration or Political Science is of interest to your. Asking such a
question may help you find an interesting topic. For example, if you are a public administration
student, you might be interest in the issue of corruption in government institutions or if you are a
political science student, you might be interested in issues of electoral violence. The principle
here is that you must identify a problem or situation you are interested in, for example domestic
violence, child defilement and many others.
Step 2. Dissect the broad areas in to subareas. From the onset, you will realize that all the areas
of interest mentioned under step 1, corruption in government institutions, electoral violence and
domestic violence have many aspects. Take domestic violence, there are many aspects and issues
in the area of domestic violence.
Once you have developed an exhaustive list of successful subareas, you proceed to the next stage
where you select what will become the basis of your inquiry.
Step 3. Select what is most of interest to you. It is neither advisable nor feasible to study all the
subareas. Out of the list, select a subarea which you are passionate about.
Step 4. Raise research questions. At this step, you ask yourself, what is it that you to find out
about the subarea you have selected. Within your chosen subarea, list what questions you want to
find answers to. If you find yourself in a situation where you have too many questions, go
through the process of elimination as you did in step 3.
22
Step 5. Formulate your objectives. Formulate your overall objective and specific objective (the
next section will focus on objectives). Your specific objectives will be derived from the research
questions. The main difference between objectives and research questions is the way they are
written. Research questions are questions which the researcher wants to find answers to.
Objectives transform these questions into behavioral aims by using words such as, to determine,
to assess, to establish, to ascertain and to find out and to examine. Note that some researchers
prefer the reverse process, that is, they start from objectives and formulate research questions
from them.
Step 6. Now examine your objectives to ascertain the feasibility of achieving them through your
research endeavor. Consider them in light of available time, expertise and resources.
Step7. Double - check. Go back and give final consideration whether you are sufficiently
interested in your study.
So far we have focused on the basis of your study, the research problem. But every research has
a second element, the respondents or people from whom information will be collected to find
answer to your research questions. As you narrow the research problem, you need to decide very
specifically who constitute your study population in order to select the appropriate respondents.
Objectives are the goals you set to attain in your study. The objectives should be listed
under two headings, the overall objective and the specific objectives. The overall objective is the
main statement of the thrust of your study. It is the statement which states what the purpose of
your study is. Specific objectives are subdivisions of the overall objective; they are specific
issues you want to investigate within the framework of your study. Specific objectives should be
numerically listed and worded clearly and unambiguously. Action oriented words should be used
when writing objectives. Each specific objective should contain only one aspect of your study.
The way the overall and specific objectives are worded determines how your research is
classified, such as descriptive, explanatory or correlational. In other words, the wording of your
objectives determines the type of research design you need to adopt to achieve them. Irrespective
of the type of research, the objectives should be clear, complete and specific. Besides the stated
23
characteristics, in correlational studies, objectives should identify the main variables to be
correlated.
As mentioned earlier, in every study there are two components; the subject area and the
population. The main aim of formulating the research problem is to clearly and precisely define
the research problem. In coming up with the research problem, you may use certain words that
may be difficult or whose understanding may vary from respondent to respondent. On the other
hand, it is also important to define clearly the study population from whom you intend to obtain
the required information. For example, the overall objective of a study may be; to investigate the
effectiveness of a training program designed to help young people. Although this objective
clearly states the main thrust of the study, it is not specific in terms of the main variables to be
studied and the study population. You cannot investigate effectiveness unless you first determine
what constitutes effectiveness. On the other hand, it is equally important to determine what you
mean by young people, up to what age would you consider someone to be young? In many cases,
you need to develop operational definitions for the variables you are studying and for the
concepts and the population which becomes a source of information for your study. In research
you need to define these clearly in order to avoid ambiguity and confusion. This is achieved
through the process of developing operational / conceptual definitions. You need to develop
operational definitions for the major concepts you are using and a framework for the study
population to enable you select appropriate respondents. Operational definitions may differ from
the dictionary definition as well as the day to day meanings.
In the construction of a research problem there are two important considerations: the use of
concepts and the construction of hypotheses. Concepts are highly subjective as their
understanding varies from person to person and therefore may not be measurable. In a research it
is important that the concepts used should be operationalised in measurable terms so that the
extent of variation in respondents’ understanding is reduced. Techniques about how to
operationalise concepts and knowledge about variables play an important role in reducing this
variability.
24
1. Definition of a variable
We all make value judgements in our everyday daily lives: ‘the food is excellent’; ‘I do not
like this’; and ‘I think this is wonderful’. These are all judgements based upon our own
preferences; the basis on which they are made may vary from person to person. There is no
uniform standard on which to measure them. A particular food may be judged as ‘excellent’ by
one person and ‘awful’ by another and something else could be wonderful to one person and
ugly to another. When people express these feelings, they do so on the basis of certain criteria in
their minds. If you take time to question them you will discover that their judgement is based
upon indicators that lead them to conclude and express that opinion.
These are judgements that require a sound basis on which to proclaim. For example, if you
want to find out if a program is effective or if a service is of quality, you need to be careful that
such judgements have a rational and sound basis. This requires the use of a measuring
mechanism and it is in the process of measurement that knowledge about variables play an
important role.
A variable is a property which takes on different values. Kerlinger (1986) defines a variable
as, an image, perception or concept that is capable of taking different values. In other words, a
concept that can be measured is called a variable. A variable can also be defined as a concept
that can be measured on any of the four types of measurement scale, which have varying degree
of precision in measurement.
Concepts are mental images or perceptions and therefore, there meanings vary from
individual to individual, whereas variables are measurable, albeit with varying degrees of
accuracy. Measurability is the main difference between a concept and a variable. A concept
25
cannot be measured whereas a variable can be subjected to measurement by objective units of
measurement. Concepts are subjective impressions; their understanding may differ from person
to person. It is therefore important that concepts are subjected to measurement even though the
degree of precision on which they can be measured varies from scale to scale.
If you are using a concept in your study, you need to consider its operationalisation or how it
will be measured. In most cases, to operationalise a concept you have to go through a process of
identifying indicators. The choice of indicators for a concept might vary with the researcher but
those selected must have a logical link with the concept. Some concepts such as ‘rich’ can easily
be converted into indicators and then variables. For example, to decide objectively if a person is
‘rich’, one needs to decide upon the indicators of richness. Assume we decide upon income and
assets as the indicator. Income is also a variable since it can be measured in numerous
currencies; therefore, you do not need to convert this into a variable. Although the assets owned
by an individual are an indicator of his or her wealth, the still belong to the category of concepts.
You need to look further at indicators of assets. For example, houses, cars and investments are
indicators of assets. Converting these assets into cash value will give a total value of the assets
owned by an individual. Thereafter, you can add the total income and value of assets to make a
decision whether one would be classified as rich.
4. Types of Variables
26
A variable can be classified in a number of ways; these classifications can be on the basis of:
causal relationship; design of the study and; unit of measurement.
a. Classification on the basis of causation – in studies that attempt to investigate the causal
relationship or association, four sets of variables may operate:
i. Change variables or independent variables, these are variables which are responsible
for bringing about change in a phenomenon.
ii. Outcome variables or dependent variables, these are variables which are the effect of
the change variable;
iii. Unmeasured Variables, these are variables which affect the link between the cause
and effect variables;
iv. Connecting or linking variables, these are variables which in a certain situation are
necessary to complete the relationship between cause and effect variables.
An independent variable is the cause responsible for bringing about change (s) in a
phenomenon or situation.
A dependent variable is the outcome of the changes brought about by introduction of an
independent variable.
Extraneous variable are several factors operating in real life situation which may affect
changes in the dependent variable. These factors may increase or decrease the
magnitude or strength of the relationship between independent and dependent variable.
Intervening variable, sometimes called confounding variables, links the independent and
dependent variables. In certain situations, the relationship between an independent and a
dependent variable cannot be established without the intervention of another variable.
The cause variable will have an assumed effect only in the presence of an intervening
variable.
27
To explain these variables let us consider some examples. Suppose you want to study the
relationship between smoking and lung cancer. You assume that smoking is a cause of cancer.
Studies have shown that there are many factors affecting this relationship, such as the number of
cigarettes or the amount of tobacco smoked everyday; the duration of smoking; the age of the
smoker; dietary habits and; the amount of exercise undertaken by the individual. All these
variables may affect the extent to which smoking may cause lung cancer. These variables may
either increase or decrease the magnitude of the relationship. In this example, smoking is the
independent variable, cancer is the dependent variable and all the variables that might affect the
relationship either positively or negatively, are extraneous variables.
c. Classification on the basis of the unit of measurement – from the view point of unit of
measurement, there are two ways of categorizing variables.
28
i. Whether the unit of measurement is categorical (as in nominal or ordinal scale) or
continuous in nature (as in interval or ratio scale);
ii. Whether it is qualitative (as in nominal and ordinal scales) or quantitative as in (interval
and ratio scales).
The variables thus classified are called categorical and continuous, and qualitative and
quantitative. On the whole, there is very little difference between categorical and qualitative and
between continuous and quantitative variables. The slight differences between them are as
follows;
Categorical variables are measured on nominal or ordinal measurement scales, whereas for
continuous variables the measurements are made either on an interval and ratio scale. Categorical
variables can be of three types;
Constant
Dichotomous
Polytomous
When a variable has only one value or category, for example taxi or water, it is known as a
constant variable. When a variable can have only two categories as in yes/no, good/bad and
rich/poor, it is known as a dichotomous variable. When a variable can be divided into more than
two categories, for example: religion (Christian, Muslim, Jew); political parties (UPND, PF,
MMD) and attitudes (strongly favourable, favourable, uncertain, unfavourable, strongly
unfavourable), it is called a polytomous variable.
Continuous variables are variables which have continuity in their measurement; for example,
age, income and attitude score. They can take on any value on the scale on which they are
measured. Age can be measured in years, months and days. Similarly, income can be measured
in kwacha and ngwees.
In many ways qualitative variables are similar to categorical variables as both use either
nominal or ordinal measurement scales. However, there are some differences. For example, it is
possible to develop categories on the basis of measurements made on a continuous scale such as
measuring the income of people on a continuous scale in kwacha and ngwee and then developing
29
categories such as low, middle and high income. The measurement of income in kwacha and
ngwee is classified as the measurement of a continuous variable, whereas the subjective
measurement in categories such as low, middle and high income groups is a qualitative variable.
It is important to understand that the way a variable is measured determines the type of
analysis that can be performed, the statistical procedures that can be applied to the data, the way
the data can be interpreted and the findings that can be communicated. The way you measure the
variables in your study determines whether a study is qualitative or quantitative in nature.
Measurement is central to any inquiry. The greater the refinement in the measurement of a
variable, the greater the confidence one can place in the findings. One of the main differences
between physical and social science is the units of measurements used and the degree of
importance attached to them. In the social sciences, the scales of measurement of variables used
are those classified by Stevens. Stevens has classified the different types of measurement scales
into four categories:
The nominal scale enables the classification of individuals, objects or responses based on a
common / shared property or characteristic. These people, objects or responses are divided into a
number of subgroups in such a way that each member of the subgroup has a common
characteristic. A variable measured on a nominal scale may have two or more subcategories
depending upon the extent of variation. For example water and tree has only one subgroup
whereas gender can be classified into two subcategories: male and female. Political parties in
Zambia can be divided in many subcategories such as UPND, PF, MMD, NAREP, ABZ,
People’s Party, New Generation Party and others. Classifications on the basis of nominal scale
ensure that individuals, objects or responses within the same subgroup have the same
30
characteristic and basis of classification. The sequence in which the subgroups are listed makes
no difference as there is no relationship among subgroups.
An ordinal scale has all the properties of a nominal scale plus one of its own. Besides
categorizing individuals, objects, responses or property into subgroups on the basis of a common
characteristic, it ranks the subgroups in a certain order. They are arranged either in an ascending
or descending order according to the extent a subcategory reflects the magnitude of variation in
the variable. For example, income can be measured either quantitatively (in kwacha and ngwee)
or qualitatively, using subcategories: above average, average and below average. These
subcategories of income are related to one another in terms of magnitude of people’s income but
the magnitude itself is not quantifiable and hence the difference between above average and
average or between average and below average subcategories cannot be ascertained. Therefore,
an ordinal scale has all the properties/characteristics of a nominal scale in addition to its own.
Subcategories are arranged in the order of magnitude. Also, the difference between the
subcategories is not equal as there is no quantitative unit of measurement.
An interval scale has all the characteristics of an ordinal scale; that is, individuals or
responses belonging to a subcategory have a common characteristic and the subcategories are
arranged in an ascending or descending order. In addition an interval scale uses a unit of
measurement that enables the individuals or responses to be placed at equally spaced intervals in
relation to the spread of the variable. This scale has a starting and a terminating point that is
divided into equally spaced units or intervals. The starting and terminating points and the number
of units/ intervals between them are arbitrary and vary from scale to scale.
Celsius and Fahrenheit scales are examples of the interval scales. In the Celsius system the
starting point (considered as freezing point) and the terminating point (considered as boiling
point) is 100ºC. The gap between freezing and boiling points is divided into 100 equally spaced
intervals, known as degrees. In the Fahrenheit system, the freezing point is 32ºF and the boiling
point is 212ºF, and the gap between the two points is divided into 180 equally spaced intervals.
As the starting and terminating points are arbitrary, they are not absolute; that is you cannot say
31
60ºC is twice as hot as 30ºC or 30ºF is three times hotter than 10ºF. This means that while no
mathematical operations can be performed on the readings, it can be performed between
readings. For example, if the difference in temperature between two objects, A and B, is 15ºC
and the difference in temperature between two other objects, C and D, is 45ºC, you cannot say
the difference in temperature between C and D is three times greater than that between A and B.
The interval scale is relative; that is, it plots the positions of individuals or responses in
relation to one another with respect to the magnitude of the measurement variable. Hence, an
interval scale has all the properties of an ordinal scale, plus it has a unit of measurement with an
arbitrary starting and terminating point. Therefore, it is relative in nature. It helps to place
individuals or responses in relation to each other with respect to the magnitude of the measuring
variable. As it is a relative scale, no mathematical operations can be performed on its readings.
The ration scale has all the properties of nominal, ordinal and interval scales, plus its own
property: the zero point of a ration scale is fixed, which means it has a fixed starting point.
Therefore, it is an absolute scale. This means ratio scales can be used for mathematical
operations. The measurement of income, weight and height are examples of this scale. A person
who is 40 years of age is twice as old as a 20 year old. A person earning K 4,000.00 per month
earns four times more than a person earning K 1,000.00.
32
of an inquiry. There are many definitions of a hypothesis, according to Kerlinger (1986), is a
hypotheses is a conjectural statement of the relationship between two or more variables. Thyer
(1993), define a hypothesis as a tentative statement about something, the validity of which is
usually unknown. Grinnell (1995) state that a hypothesis is written in such a way that it can be
proven or disproven by valid and reliable data, it is in order to abtain these data that we perform
our study. From the above definitions, it is certain that a hypothesis has certain characteristics:
It is a tentative preposition.
Its validity is unknown.
In most cases, it specifies a relationship between two or more variables.
a. The formulation of a hypothesis provides a study with focus. It tells you what specific
aspects of a research problem to investigate.
b. A hypothesis tells you what data to collect and what not to collect thereby providing a
focus for your study.
c. As it provides a focus, the construction of hypotheses enhances objectivity in a study.
d. A hypothesis may enable you to add to the formulation of a theory. It enables you to
conclude what is true and what is false.
2. Characteristics of a hypothesis
a. A hypothesis should be simple, specific and conceptually clear. Ambiguity in the
construction of a hypothesis will make the testing of the hypothesis impossible. A
hypothesis should only test one relationship or hunch at a time. The more insight you
have in an area, the easier it is to construct a hypothesis.
b. A hypothesis should be capable of verification. Methods and techniques must be
available for data collection and analysis.
c. A hypothesis should be related to existing body of knowledge. It is important that your
hypothesis emerges from the existing body of knowledge and that it adds to it as this is an
33
important function of research. This can only be achieved if the hypothesis has its roots in
the existing body of knowledge.
d. A research hypothesis should be operationalised. This means that it can be expressed in
terms that can be measured. If it cannot be measured, it cannot be tested hence no
conclusion can be drawn.
3. Types of hypothesis
As explained earlier, any assumption that you seek to validate through an inquiry is called a
hypothesis. Hence, theoretically there should be only one type of hypothesis, that is, the research
hypothesis – the basis of your investigation. However, because of the wording used in the
construction of a hypothesis, hypothesis can be broadly classified into two categories:
a. Research hypothesis
b. Null hypothesis
34
Any, some or all of these aspects of the research process could be responsible for the
inadvertent introduction of error in your study, making conclusions misleading. Hence, in the
testing of a hypothesis, there is always the possibility of errors attributable to the identified
reasons. In drawing conclusions about a hypothesis, two types of errors can occur.
a. Types I error. This is the error of rejecting a null hypothesis when it is true.
b. Type II error. This is the error of accepting a null hypothesis when it is false.
7.0 Summary
You have been informed in this unit that a research problem is any idea or issue which
becomes the basis of your research and that most research problems in Public Administration and
Political Science revolve around people, problems, programs and phenomenon. At this point you
must also understand that variables are the building blocks of research and that they are
classified on the basis of causation, study design, unit of measurement and type of measurement.
There are two types of hypothesis, the research hypothesis and the null hypothesis. The research
hypothesis is what the researcher is interested in testing and the null hypothesis is the antithesis
of the research hypothesis.
After reading through unit three, you should answer the question below. It is
important for you to attempt the question in order to gauge how much you have comprehended
the material presented in this unit. If you are having challenges in answering the question, read
unit three again.
a. Variable
b. Concept
c. Type I error
35
d. Objectives
36
UNIT FOUR: THE RESEARCH DESIGN
1.0 Introduction
This unit focuses on research design. The unit begins by defining research design and
explaining the functions of a research design. Thereafter, we will then categorise research
designs based on the number of contacts with the study population, the reference period of the
study and the nature of the investigation.
The aim of this unit is to explain the various types of research design.
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Nachimias, D. and Nachimias, D. (1996), Research Methods in Social Sciences, 5th Ed,
London: St. Martin Press
It will take you approximately three hours to work through this unit.
37
6.0 Main Contents
The above definitions suggest that a research design has two main functions. The first relates
to the identification and / or development procedures and logistical arrangements necessary to
undertake research, and the second emphasizes the importance of quality in these procedures to
ensure their validity, accuracy and objectivity. Hence through research design you:
Conceptualize an operational plan to undertake the various procedures and tasks requires
to complete your study;
Ensure that these procedures are accurate to obtain valid, objective and accurate answers
to the research questions
The first function of the research design which relates to the overall plan of the study details
all the procedures and tasks the researcher will perform to obtain answers to the research
questions. One of the most important requirements of the research design is to specify everything
clearly so that a reader will understand what procedures to follow and how to follow them. A
research design therefore should do the following:
1. Name the study design e.g. cross – sectional, comparative, before and after, etc.
2. Provide detailed information about the following aspects of the study
a. Who will constitute the study population?
b. How will the study population be identified?
c. Will a sample or the whole population be selected?
38
d. How will consent be thought?
e. What methods of data collection will be used and why?
f. How will data be collected using the stated instruments?
g. How will ethical issues be considered?
There are various kinds of study designs. The designs can be classified by examining them
from three different perspectives.
Based on the number of contacts with the study population, designs can be classified into
three groups; cross-sectional studies; before and after studies and longitudinal studies.
Cross – sectional studies, also known as one-shot or status studies are most commonly used
designs in the social sciences. This design is best suited to studies aimed at finding out the
prevalence of a phenomenon, situation, problem, attitude or issue, by taking a cross – section of
the population. They are important for obtaining an overall picture as it stands at the time of the
study. Such studies are cross-sectional with regard to both the study population and the time of
investigation.
A cross-sectional study is extremely simple in its design. You decide what you want to find
out, identify the study population, select a sample (if you need to) and contact your respondents
to find out the required information. Cross-sectional studies involve only one contact with the
study population, they are comparatively cheap to undertake and easy to analyze. However, their
biggest disadvantage is that they cannot measure change. To measure change, it is necessary to
have at least two data collect points – that is at least two cross-sectional studies, at two points in
time, on the same population.
39
b. The before-and –after study design
A before-and-after study can be described as two sets of cross-sectional data collection points
on the same population to find out the change in a phenomenon or variables between two points
in time. The change is measured by comparing the differences in the phenomenon or variables
before and after the intervention. A before- and- after study is carried out by adopting the same
process as a cross-sectional study except that it comprises two cross-sectional observations, the
second being undertaken after a certain period. This sort of design is commonly used in
evaluative studies. The difference between the two data collection points is considered to be the
impact of the program. Examples of topics which can be studied using this design: The impact of
incentives on productivity of employees in an organization; The impact of increased funding on
the quality of teaching in universities; The impact of administrative restructuring on the quality
of services provided by an organization and; and the impact of advertising on the sales of a
product.
The main advantage of the before-and-after study is its ability to measure change in a
phenomenon or to assess the impact of an intervention. However, it has disadvantages such as; it
is expensive and more difficult to implement; the time lapse between the two may results in
attrition in the study population; it cannot ascertain whether change can be attributed to the
independent variable or extraneous variables; maturation effect and; reactive effect.
This is a study design used to determine the pattern of change in relation to time. A
longitudinal study is used when you wish to study the proportion of people adopting a program
in relation to time. Longitudinal studies are also useful when you need to collect factual
information on a continuing basis. In longitudinal studies, the study population is visited a
number of times at regular intervals, over a long period to collect the required information. These
intervals are not fixed so their length may vary from study to study. Irrespective of the size of the
interval, the information gathered each time is identical. Although the data collected in from the
same population, it may or may not be from the same respondents. A longitudinal study can be
seen as a series of repetitive cross-sectional studies.
40
The main advantage of a longitudinal study is that it allows the researcher to measure the
pattern of change and obtain factual information, requiring collection on regular or continuing
basis, thus enhancing its accuracy. However, longitudinal studies have the same disadvantages as
the before-and-after studies. In addition, longitudinal studies can suffer from the conditioning
effect. This describes a situation where the same respondents are contacted frequently, they
begin to know what is expected of them and may respond to the questions without thought.
i. Trend studies – these are studies in which the research studies changes within some
general population overtime. For examples, somebody studying opinion polls to
determine political candidate preferences over the course of campaigns
ii. Cohort studies - a cohort is a group of people with shared characteristics, for example a
group of PAS 2014 students. These studies tend to focus on specific samples of the
population as they change overtime.
iii. Panel studies – these share the same characteristics with cohort studies because they
focus on the same set of people. The difference is that cohort focus characteristics of
people but different sets of people while panel studies focus on same sets of people with
same characteristics.
The reference period refers to the time frame in which a study is exploring a phenomenon,
situation, event or problem. Studies within this perspective are thus classified as: retrospective;
prospective and; retrospective-prospective.
41
b. The prospective study design
Retrospective-prospective studies focus on past trends in a phenomenon and study it into the
future. A study is classified under this category when you measure the impact of an intervention
without having a control group. In a retrospective-prospective study a part of the data is collected
retrospectively from existing records before the intervention is introduced and then the study
population is followed to ascertain the impact of the intervention.
On the basis of the nature of the investigation, studies may be classified as: experimental;
non experimental and; and quasi or semi experimental. To understand the difference, let us look
at one example. Suppose you want to find out the impact of a particular teaching method on the
level of students’ performance. In such a situation there is cause and effect relationship. The first
involves the researcher or (someone else) introducing the intervention that is assumed to be the
cause of change and waiting until it has produced – or has been given sufficient time to produce-
the change. The second involves the researcher observing a phenomenon and attempting to
establish what caused it. In this instance, the researcher starts from the effects or outcome and
attempts to determine causation. If a relationship is studied in the first way, starting from the
cause to establish the effects, it is classified as an experimental study. If the second option is
followed - that is, starting from the effects to track the cause – it is classified as a non
experimental study. In the case of an experimental study, the independent variable can be
observed, introduced, controlled or manipulated by the researcher. Whereas in a non
experimental study this cannot happen as the assumed cause has already occurred. Instead, the
researcher retrospectively links the causes to the outcomes. A quasi or semi experimental study
has the properties of both the experimental and non experimental studies; part of the study may
be experimental and the other part non experimental.
42
a. Experimental designs
These are research designs in which you can prove causality. In an experimental study,
individuals are randomly assigned to the experimental and control groups and the researcher
makes observations. The main characteristic of an experimental design are;
This is a kind of research design where one characteristic of the experimental design is
missing. It is either the use of control or randomization or both but manipulation is always
present. In terms of its structure, it resembles the experimental design as it uses one or more
control groups and the same procedures are followed.
c. Non-experimental design
This is a kind of research design where the researcher just describes and analyses the
research subjects and the situation in which they are found without any intervention. The
researcher undertakes the research in the situation as it found.
a. Case studies –The case study method is an approach to studying social phenomenon
through a thorough analysis of an individual case. The case may be a person, individual,
process, community, episode, society or any other unit of social life. All data relevant to
the case are gathered and organized in terms of social life. It provides an opportunity for
the intensive analysis of many specific details often overlooked by other methods. This
approach rests on the assumption that the case being studied is typical of cases of a
43
certain type, that it, through intensive analysis; generalizations may be made that will be
applicable to other cases of the same nature.
b. Descriptive studies – these studies involve the systematic collection and presentation of
data in order to have a very clear picture of a given situation or problem. Descriptive
studies require a greater degree of accuracy and precision in the manner in which you
report events.
c. Analytical studies- these studies attempt to establish the causes of risk factors for certain
problems. They seem to unravel factors underlying a particular problem.
d. Evaluation studies. Evaluation studies are concerned with the description or explanation
of programs and policies. Evaluation deals with assessing programs that have been
implemented. Not only do evaluation studies add knowledge, but they also assess in order
to take a particular action to correct the situation. Evaluation studies have no
methodology of their own but use the same techniques used in research. The difference
with other research studies is in the purpose and objectives. Evaluation is undertaken
based on the following criteria: effort; efficiency; effectiveness; and impact.
7.0 Summary
In this unit you have been informed that a research design is a complete scheme or
plan of how the research will be conducted. You have been further informed that when you
examine a research design on the number of contacts with the study population, you have the
cross – sectional study design, the before and after study design and the longitudinal study
design. When you examine a research design based on the reference period, you have the
retrospective study design, the prospective study design and the retrospective – prospective study
design. When you analyse a research design based on the nature of the investigation you have the
experimental study designs, quasi or semi experimental study designs and non – experimental
study designs.
44
8.0 Self Assessment Questions
After reading through unit four, you should answer the question below. It is important
for you to attempt the question in order to gauge how much you have comprehended the material
presented in this unit. If you are having challenges in answering the question, read unit four
again.
1.0 Introduction
This unit discusses the approaches to data collection and how to construct the instruments for
data collection. The unit begins by explaining the meaning of primary data and thereafter
discusses different techniques for collecting primary data and how to design data collection tools.
Thereafter, we will focus identifying and examining categories of secondary data.
45
The aim of this unit is to enable you design instruments for data collection.
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Grinnel, R. (1995), Research and Evaluation, Illinois: Peacock Publishers
It will take you approximately two hours thirty minutes to work through this unit.
There are two major approaches to gathering information about a situation, person, problem
or phenomenon. Sometimes information required is already available and need only to be
extracted. However, there are times when the information must be collected. Based upon the
broad approaches to information gathering data are classified as:
Secondary data
46
Primary data
Information gathered using the first approach is said to be collected from secondary sources
whereas the sources used in the second approach are called primary sources. Examples of
secondary sources include the use of census data to obtain information on the age, sex and
structure of the population; the use of hospital records to find out the morbidity or mortality
patterns of a community; the use of an organization’s records to ascertain its activities and the
collection of data from sources such as journals, magazines, books, articles and periodicals to
obtain historical and other types of information. On the other hand, finding out first-hand the
attitudes of a community towards health services, ascertaining the health needs of a community,
evaluating a social program and ascertaining the quality of services provided by a worker are
examples of information collected from primary sources. Therefore, primary data provides first
hand information while secondary data provides second hand information.
Several methods can be used to collect primary data. The choice of a method depends on the
purpose of the study. In selecting data collection methods, the socio-economic and demographic
characteristics of the study population play an important role: some populations for example may
not feel at ease with a particular method of data collection (such as being interviewed) or
comfortable to express opinions in a questionnaire. Furthermore, people with little or no
education may respond differently to certain methods of data collection compared to highly
educated people. Another important determinant of the quality of your data is the way the
purpose and relevance of your study is explained to potential respondents. Whatever method of
data collection is used, make sure that respondents clearly understand the purpose and relevance
of your study. The following are some of the methods of collecting primary data:
1. Observation
47
cannot be obtained through a questionnaire, because respondents either are uncooperative or are
unaware of the answers because it is difficult for them to detach themselves from the interaction.
In summary, when you are more interested in the behavior than in the perceptions of individuals
or when subjects are so involved in the interaction that they are unable to provide objective
information about it, observation is the best approach to collect the required information.
There are two types of observations; participant observation and non-participant observation.
The advantages of observations are that; they provide first hand information as the researcher
gets insight of the context in which things happen. However, the disadvantages of observations
are that individuals tend to act when they know that they are being watched hence the observer
might have a distorted view of things (the Hawthorne effect); there is a possibility of bias as the
observer may only record things of interest to him/her and eliminating things not seen to be of
interest; and observations are time consuming and the information gathered may be subjective.
2. Interviews
Interviews are a commonly used method of collecting information from people. In many
walks of life, we collect information through different forms of interaction with others. Any
person – to -person interaction between two or more individuals with a specific purpose in mind
48
is called an interview. On the one hand, interviews may be flexible, when the interviewer has the
freedom to formulate questions as they come to mind around the issue being investigated; and on
the other hand, it can be rigid, when the investigator has to stick strictly to the questions decided
before hand. Therefore, there are two main types of interviews, unstructured interviews and
structured interviews.
a. Unstructured interviews
The strength of unstructured interviews is the almost complete freedom they provide in terms
of content and structure. You are free to order these in whatever sequence you wish. You also
have complete freedom in terms of the wording you use and the way you explain questions to
your respondents. You may formulate questions or raise issues on the spur of the moment,
depending on what occurs to you in the context of the discussion.
There are several types of unstructured interviews; for example: in-depth interviews, narratives
and oral histories.
i. In-depth interviews
In-depth interviews are a repeated face to face encounter between the researcher and the
informant directed towards understanding the informants’ perspective on their lives, experiences
or situations as expressed in their own words. Because of the extended length of time spent with
an informant, it is assumed that the rapport between the researcher and the informant will be
enhanced and the corresponding understanding between the two will lead to in-depth and
accurate information.
The difference between a focus group discussion and an in-depth interview is that the former
is undertaken with a group and the latter with an individual. In a focus group discussion, you
explore the perceptions, experiences and understandings of a group of people who have some
experiences in common with regard to a situation or event. In a focus group discussion, broad
discussion topics are developed before hand, these provide a frame for the discussion which
follows. Members of the group express their opinions while discussing these issues. In a focus
49
group discussion, an interview guide is used by the researcher and as a researcher; you need to
ensure that whatever is expressed by the informants is recorded.
iii. Narratives
The narrative technique of gathering information has even less structure than the focus group
discussion. Narratives have almost no pre-determined contents except that the researcher seeks to
hear the personal experience of a person with an incident happening in his or her life. Essentially,
the person tells his or her story about an incident or situation and you as the researcher listen
passively. Narratives are a very powerful method of collecting data for situations which are
sensitive in nature. As with focus group discussions, the researcher needs to choose a recording
system that suits him/her best.
Oral histories like narratives involve passive and active listening. Oral histories are however
commonly used for learning about a historical event or episode that took place in the past or for
gaining information about a cultural, custom or story that has been passed from generation to
generation. Narratives are more about personal experiences whereas historical, social or cultural
events are the subjects of oral histories.
Data collected through unstructured interviews is extremely useful in situations where either
in-depth information is needed or little is known about the area. The flexibility allowed to the
interviewer helps in the acquisition of comprehensive information during the interview. On the
other hand, since unstructured interviews do not list all the specific questions to be asked of
respondents, the comparability of questions asked and responses obtained may become a
problem. As a researcher gains experience during the interviews, the questions asked to
respondents change; hence, the type of information obtained from those who are interviewed at
the beginning may be different from those who are interviewed towards the end. Using an
interview guide as a means of data collection requires much more skill on the part of the
researcher than does using a structured interview.
b. Structured interviews
50
In a structured interview the researcher asks pre-determined questions, using the same
wording and order of questions as specified in the interview schedule. An interview schedule is a
written list of questions, open-ended or close-ended, prepared for use by an interviewer. One of
the main advantages of a structured interview is that it provides uniform information, which
ensures the comparability of data. Structured interviews require fewer interviewing skills than
unstructured interviews.
i. The Questionnaire
The advantages of a questionnaire are that; it is less expensive when self administered; it
offers greater anonymity thus in situations where sensitive questions are asked, it enables
respondents to answer freely. However, the disadvantages of a questionnaire are that: When self
administered, its application is limited to a study population that can read and write; the
opportunity to clarify issues by the researcher is lacking; and it is possible that a respondent may
consult other.
It is essential that your questionnaire has a cover letter. The letter should briefly: introduce
you and the institution you are representing; describe in full or few sentence the main objectives
of the study; explain the relevance of the study; convey any general instructions; indicate that
participation in the study is voluntary if respondents do not want to respond to the questionnaire
they have the right to; assure respondents of confidentiality of the information provided by them;
and thank them for their participation in the study.
51
b. Types of questions
i. Background questions
These are the first set of questions in a questionnaire which elicit information about the
background information of the respondent. These question capture information on demographic,
(e.g age, sex), social (e.g level of education, marital status, religious affiliation) and economic
(i.e employment, income) characteristics of respondents.
In an interview schedule or questionnaire there are two types of questions namely open ended
and close ended questions. In open ended questions the possible responses are not given. In case
of a questionnaire, the respondent writes the answer in his or her own words whereas in the case
of an interview schedule the investigator (researcher) records the answer either verbatim or in a
summary describing the respondent’s answer. In close ended questions, the possible answers are
given in the questionnaire or interview schedule and the respondent or investigator (researcher)
ticks the response that best describes the respondent’s answer.
The advantages of open ended questions are that; they provide in-depth information if used
by an experienced interviewer; respondents are given an opportunity to express themselves freely
and are thus not conditioned to answer in a certain way; and as they allow the respondent to
answer freely, they eliminate the possibility of investigator bias. The disadvantages of open
ended questions are that; the analysis of open ended questions is more difficult; since
respondents are not give option, there is a possibility that some respondents may not be able to
express themselves so information may be lost; and there is greater chance of interviewer bias.
The advantages of close ended questions are that: they are easy to analyze; they are easy to
answer; because response categories are provided, they ensure that the information needed by the
researcher is obtained. However, the disadvantages of close ended questions are that: the
information obtained lacks depth and clarity; there is a greater possibility of investigator
(researcher) bias because the researcher might only list responses that are of interest to him/her;
and answers provided may not reflect the respondent’s opinion.
52
iii. Filter questions
These are questions which apply only to a certain segment of the population. They lead to
contingency question those which are contingent upon the response from the filter question. For
example: Q8. Are you a member of any political party? 1. Yes ( ) 2. No ( ). If your answer to
Q8 is No, skip question Q9. The questionnaire can then have a follow up question which can
read as: Q9. Which political party do you support? In this example, Q8 is a filter question while
Q9 is a contingency question.
A contingent question is a question which is dependent on how one has answered a preceding
question. Whether a respondent has to answer a question is dependent (contingent) on how
he/she has answered the preceding (filter question). Answering Q9, Which political party do you
support? Is contingent (dependent) on your answer to Q8, Are you a member of any political
part?
v. Rating questions
These are questions in which respondent are allowed to make judgments in terms of sets of
ordered categories. For example: How happy are you with your conditions of service?
1. Very happy ( )
2. Happy ( )
4. Unhappy ( )
5. Very unhappy ( )
A matrix question is a question which has a large number of questions with similar response
categories which are grouped together.
53
For example: How would you describe the following infrastructure at your school?
Q13. How would you describe the following infrastructure at your school?
Very Good Average Bad Very Bad
Good
A. Library
B. Hostel
C. Classrooms
D. Canteen
The wording and tone of your questions are important because the information obtained and
its quality largely depends on these factors. It is therefore important to be careful about the way
you formulate questions. The following are some considerations to keep in mind when
formulation questions:
a. Always use simple and everyday language – your respondents may not be highly
educated and even if they are they still may not know some of the simple technical jargon
that you are used to. Particularly in a questionnaire, take extra care to use words that your
respondents will understand as you have no opportunity to explain questions to them. A
pre-test should show you what is and what is not understood by your respondents.
b. Do not use ambiguous questions – an ambiguous question is one that contains more than
one meaning and that can be interpreted differently by different respondents. This will
result in different answers making it difficult to draw any valid conclusion from the
information. For example, ‘Are you satisfied with your canteen?’1. Yes ( ) 2. No ( ).
This question is ambiguous as it does not ask respondents to indicate the aspect of the
canteen which they may be satisfied or dissatisfied with. Is it with the services? The
attitude of staff or the quality of meals? Respondents may have any of these aspects when
answering the question.
c. Do not ask double - barreled questions. A doubled – barreled question is a question
within a question. The main problem with this type of question is that one does not know
54
which particular question a respondents has answered. Some respondents may answer
both questions and some may only answer one of them. For example, ‘How often and
how much time do you spend in a queue at the clinic?’ In the type of question, some
respondents may answer the first part, whereas other may answer the second and some
may answer both parts.
d. Do not ask leading questions – a leading question is one which by its content, structure or
wording, leads the respondent to answer in a certain way. Such questions are judgemental
and lead respondents to answer either positively or negatively. For example,
‘Unemployment is increasing, isn’t it?’ With such a question, a respondent may think to
disagree with it is to be in the wrong. The feeling that there is a right answer can force
people to respond in a way that is contrary to their true position.
e. Do not ask questions that are based on presumptions – in such questions, the researcher
assumes that respondents fit into a particular category and seeks information based upon
that assumption. For example, ‘How many cigarettes do you smoke in a day?’ This
question is asked without ascertaining whether or not the respondents are smokers. In
situation like this, it is important to first ascertain whether or not a respondent fits into a
category about which you are inquiring.
There are occasions when the information required by your study has already been collected
by someone else and you only need to extract it for the purpose of your study. There are many
categories of secondary data, among them are the following;
a. Government or non - government publications – there are many government and non -
governmental organisations that collect data on a regular basis in a number of areas and
publish it for use by members of the public and other interest groups. Some common
example are the census, labour force surveys, health reports, reports by commissions of
inquiry, reports by parliamentary select committees, reports by government ministries,
departments and reports by civil society organizations.
b. Earlier research – for some topic, an enormous number of research studies that have
already been done by other can provide you with the required information
55
c. Mass media – reports published in newspaper, magazines, internet and so on may be
another good source of data.
When using secondary data, you will need to be careful as there may be certain problem with
the availability, format and quality of data. The extent of these problems varies from source to
source. While using such data, some issues you should keep in mind are:
a. Validity and reliability – the validity of the information may vary from source to source.
For example, information from a government agency or a reputable civil society
organization is likely to be more valid and reliable than that obtained from a personal
diary.
b. Personal bias – the use of information from personal diaries, newspapers and magazines
may have a personal bias as these writers are likely to exhibit less rigorousness and
objectivity than one would expect in research reports.
c. Availability of data – it is common for researchers to assume that the required data will
be available, but you should not make this assumption. Therefore, it is important to make
sure that the required data are available before proceeding further with your research.
7.0 Summary
In this unit you have been informed that primary data and secondary data are the two
major approaches to gathering information in research. Primary data can be collected through
observation and interviews. There are two types of observations, participant observation and non
participant observation. We have divided interviews into unstructured interviews and structured
interviews. Unstructured interviews include in-depth interviews, Focus Group Discussions
(FDGs), narratives and oral histories. On the other hand, structured interviews entail the use of
questionnaires.
56
After reading through unit five, you should answer the question below. It is important
for you to attempt the question in order to gauge how much you have comprehended the material
presented in this unit. If you are having challenges in answering the question, read unit five
again.
1.0 Introduction
This unit discusses the concept of sampling in both qualitative and quantitative research. The
unit begins by defining the concepts of sampling. We will then explain sampling terminologies
and identify principles of sampling. Thereafter, we shall look at major sampling designs namely;
probability sampling designs and non probability sampling designs.
The aim of this unit is to explain the concept of sampling in both quantitative and qualitative
research.
57
Explain different sampling designs.
Indicate the major terminologies used in sampling.
Outline the principles of sampling.
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Grinnel, R. (1995), Research and Evaluation, Illinois: Peacock Publishers
McNabb, D. (2009), Research Methods for Political Science: Quantitative and
Qualitative Methods, New Delhi: PHI Learning Private Limited
It will take you approximately three hours to work through this unit.
Let us take a very simple example to explain the concept of sampling. Suppose you want
to estimate the average age of the students in your class. There are two ways of doing this. The
first method is to contact all students in the class, find out their ages, add them and then divide
the answer by the number of students. The second method is to select a few students from the
class, ask them their ages, and add them up and then divide by the number of students you have
58
asked. From this you can make an estimate of the average age of the class. Take another
example: Suppose you want to find out the average income of families living in a city. You could
follow the procedure described above, but imagine the amount of effort and resources required to
go to each family in the city to find out their income. You could follow the second method by
selecting a few families to become the basis of your inquiry, and then, from what you have found
out from the few families, make an estimate of the average income of families in the city. A
further example would be the outcome of an election: the results are decided after voting on
election day, but predictions about the outcome are usually made on the basis of the outcomes of
opinion polls. These polls are based upon a very small group of people who are asked about their
voting preferences. On the basis of these results, a prediction is made about the outcome.
Sampling is a process of selecting a few (a sample) from a bigger group (the sampling
population) to become the basis for estimating or predicting the prevalence of an unknown piece
of information, situation or outcome regarding a bigger group. A sample is the subgroup of a
population you are interested in.
This process of selecting a sample from the population has advantages and disadvantages.
The advantages are that it serves time as well as financial and human resource. However, the
disadvantage is that you do not find out the information about the population’s characteristics of
interest to you but only estimate or predict them. Hence, the possibility of an error in your
estimation exists.
Sampling is thus a trade- off between certain gains and losses. While on one hand you
serve time and resources, on the other hand you may compromise the level of accuracy in your
findings. Through sampling, you only make an estimate about the actual situation prevalent in
the total population from which the sample is drawn. If you collect a piece of information from
the total sampling population and if your method of inquiry is correct, your findings should be
reasonably accurate. However, if you select a sample and use this information as the basis for
estimating the situation in the total population, an error is possible. Tolerance of this possibility
of error is an important consideration in selecting a sample.
59
In qualitative research the issue of sampling has little significance as the main aim of
most qualitative inquiries is either to explore or describe the diversity in a situation, phenomenon
or issue. Qualitative research does not make an attempt to either quantify or determine the extent
of this diversity. You can select even one individual as your sample and describe whatever the
aim of your inquiry is. A study based upon the information obtained from one individual, or
undertaken to describe one event or situation is perfectly valid. In qualitative research, to explore
the diversity, you need to reach what is known as saturation point in terms of your findings; for
example, you go on interviewing or collecting information as long as you keep discovering new
information. When you find that you are not obtaining any new data or the new information is
negligible you are assumed to have reached saturation point. Some researchers prefer to select as
sample with non-probability designs and to collect data till they have reached saturation point.
Keep in mind that saturation point is subjective judgement which you, as a researcher, decide.
Let us, again, consider one example from those used above. Our main aim is to find out the
average age of the class. Let us assume that we adopt the second method- that is, to select a few
students to achieve these aims. In this process, there are a number of aspects:
Population or study population. The class from which you select a few students to ask
questions in order to answer your research questions is called the study population or
population and is usually denoted by the letter (N)
Sample. The small group of students from whom you collect the required information to
estimate the average age of the class.
Sample size. This is the number of students from whom you collect the required
information. Sample size is usually denoted by the letter (n)
Sampling design or strategy. The way you select students to include in the sample is
called sampling design or strategy.
Sampling unit or sampling element. Each student that becomes the basis for selecting
your sample is called a sampling unit or element.
Sampling frame. A list of all the students in a class is the sampling frame. If all the
elements in a study population cannot be individually identified, you cannot have a
sampling frame for that study population.
60
Sample statistics. These are findings based on the information obtained from your
respondents (sample). Your sample statistics become the basis for estimating the
prevalence of a situation or phenomenon in the population.
Population parameters / population mean. The main aim of sampling is to find answers
to your research questions and not for the sample you collect answers from. In the case of
the example on the average age of students in a class, from the sample statistics, we make
estimate of the answer to the research question in the study population. The estimates
arrived at from sample statistics are called population parameters or population mean.
Values obtained from a sample are called statistics while values obtained from the study
population are called parameters.
Now let us suppose that you want to select a sample of two individuals to make an estimate
of the average age of the four individuals. If you adopt the theory of probability, we can have six
possible combinations of two: A and B; A and C; A and D; B and C; B and D; and C and D. Let
us take each of these pairs to calculate the average age of the sample:
Notice that in most cases the average age calculated on the basis of these samples of two
(sample statistics) is different. Now compare these sample statistics with the average of all four
individuals – the populations mean (population parameter of 21.5 years). Out of a total of six
61
possible sample combinations, only in the case of two is there no difference between the sample
statistics and the population mean. Where there is a difference, this is attributed to the sample
and is known as sampling error. Again, the size of the sampling error varies markedly. Let us
consider the difference in the sample statistics and the population mean for each of the six
samples.
Principle 1, in a majority of cases of sampling there will be a difference between the sample
statistics and the true population mean, which is attributed to the selection of the units in the
sample.
To understand the second principle, let us continue with the above example, but instead of a
sample of two individuals, take a sample of three. There are four possible combinations of the
three that can be drawn.
Now, let us compare the difference between sample statistics and the population mean.
62
Table 2: Differences between Sample Statistics and Population Parameters
Sample Sample average Population mean Difference between
(sample statistics) (population parameter) (1 ) and (2)
1 2
1 20.33 21.5 -1.17
2 21.00 21.5 -0.5
3 22.00 21.5 +0.5
4 22.67 21.5 +1.17
Compare the difference between the differences calculated in the first and second table.
In the first table, the difference between the sample statistics and the population mean lies
between -2.5 and +2.5 years, whereas in the second table it is between -1.17 and +1.17 years.
The gap between the sample statistics and the population mean is reduced in table two. This
reduction is attributed to the increase in the sample size. This, therefore, leads to the second
principle:
Principle 2, the greater the sample size, the more accurate will be the estimate of the true
population mean.
Let us follow the same procedure, selecting samples of two individuals at a time and then
three. If we work through the same procedures (described above we will find that the difference
in the average age in the case of two samples ranges between -7.00 and +7.00 years and in the
case of a sample of three ranges between -3.67 and +3.67. In both cases the range of the
differences is greater than previously calculated. This is attributable to the greater difference in
63
the ages of the four individuals – the sampling population. In other words, the sampling
population is more heterogeneous in regards to age.
Principle 3, the greater the difference in the variable under study in a given population for a
given sample size, the greater will be the difference between the sample statistics and the true
population mean.
These principles are crucial to keep in mind when you are determining the sample size
needed for a particular level of accuracy, and in selecting the sample strategy best suited to your
study.
There are various types of sampling strategies and these can be categorized a follow:
For a sampling design to be called random or probability sample, it is imperative that each
element in the population has an equal and independent chance of selection in the sample. Equal
implies that the probability of selection of each element in the population is the same; that is, the
choice of an element in the sample is not influenced by other consideration such as personal
preferences. The concept of independence means that the choice of one element is not dependent
upon the choice of another element in the sampling; that is, the selection or rejection of one
element does not affect the inclusion or exclusion of another.
A random sample can be drawn using methods such as fishbowl draw, computer program
and a table of random numbers. A fishbowl method involves numbering each element in your
study population using a separate slip of paper for each element, put all the slips into a box, and
64
then pick them out one by one without looking, until the number of slips you have selected
equals the sample size you decided upon. Computer programs or software can also be used to
select elements randomly from the sampling frame which is entered into the software by the
researcher. The researcher commands the computer to randomly select a number of elements
equal to his sample size.
There are three commonly used types of random / probability sampling designs:
i. Simple random sampling (SRS) – this is the most commonly used method of
selecting a probability sample. In line with the definition of randomization, whereby
each element in the population is given an equal and independent chance of selection,
a simple random sample is selected by the following procedure. Firstly, identify by a
number all elements or sampling units in the population, secondly decide on the
sample size (n) and thirdly select (n) using either the fish bow draw, the table of
random numbers of a computer program.
To illustrate, let us again take our example of a class. There are 80 students in the class, and
so the first step is to identify each student by a number from 1 to 80. Suppose you decide to
select a sample of 20 using a simple random technique. Use either the fish bow draw, the table
for random numbers or a computer program to select the 20 students. These 20 students become
the basis of your inquiry.
ii. Stratified random sampling – As discussed, the accuracy of your estimate largely
depends on the extent of variability or heterogeneity of the study population with
respects to the characteristics that have a strong correlation with what you are trying
to ascertain ( principle 3). It follows, therefore, that if the heterogeneity in the
population can be reduced by some means for a given sample size you can achieve
greater accuracy in your estimates. Stratified random sampling is based upon this
logic. In stratified random sampling, the researcher attempts to stratify the population
in such a way that the population within a stratum is homogeneous with respect to the
characteristic on the basis of which it is being stratified. It is important that the
characteristics chosen as the basis of the stratification are clearly identifiable in the
65
study population. For example, it is much easier to stratify a population on the basis
of gender than on the basis of age, income or attitude. It is also important for the
characteristic that becomes the basis of stratification to be related to the main variable
that you are exploring. Once the sampling population has been separated into non-
overlapping groups, you select the required number of elements from each stratum,
using the simple random technique. There are two types of stratified sampling:
proportionate and disproportionate stratified sampling. With proportionate stratified
sampling, the number of elements in each stratum in relation to its proportion in the
total population is selected, whereas in disproportionate stratified sampling,
consideration is not given to the size of the stratum.
iii. Cluster sampling – simple random and stratified sampling are based on the
researchers’ ability to identify each element in a population. It is easy to do this if the
total sampling population is small, but if the population is large, as in the city, state or
country, it becomes difficult and expensive to identify each sampling unit. In such
cases, the use of cluster sampling is more appropriate. Cluster sampling is based on
the ability of a researcher to divide the sampling population into groups, called
clusters, and then to select elements within each cluster, using the simple random
selection technique. Cluster can be formed on the basis of geographical proximity or a
common characteristic that has a correlation with the main variable of a study (as in
stratified sampling). Depending on the level of clustering, sometimes sampling can be
done at different levels. These levels constitute the different stages (single, double,
multi) of clustering.
b. Non random / non probability sampling design
Non probability sampling designs do not follow the theory of probability in the choice of
elements from the sampling population. Non – probability sampling designs are used when the
number of elements in the population is either unknown or cannot be individually identified. In
such as situation, the selection of elements is dependent upon other considerations. There are
four non random designs, each based on a different consideration, which are commonly used in
qualitative and quantitative research:
Quota sampling
66
Purposive sampling
Snowball sampling
Convenience sampling
i. Quota sampling. The main consideration directing quota sampling is the researcher’s
ease of access to the sample population. In addition to convenience, the researcher is
guided by some visible characteristic, such as gender or race, of the study population
that is of interest to the researcher. The sample is selected from a location convenient
to the researcher, and whenever a person with these visible relevant characteristics is
seen, that person is asked to participate in the study. The process continues until the
researcher has been able to contact the required number of respondents (quota).There
are advantages and disadvantages with this design. The advantages are: it is the least
expensive way of selecting a sample; you do not need any information, such as a
sampling frame, the total number of elements, their location or other information
about the sampling population; and it guarantees the inclusion of the type of people
you need. The disadvantages are: as the resulting sample is not a probability one, the
findings cannot be generalized to the total sampling population; and the most
accessible individuals might have characteristics that are unique to them and hence
might not be truly representative of the total sampling population.
ii. Purposive sampling. The primary consideration in purposive sampling is the
judgement of the researcher as to who can provide the best information to achieve the
objectives of the study. The researcher only goes to those people who in his or her
opinion are likely to have the required information and be willing to share it. This
type of sampling is extremely useful when you want to construct a historical reality,
describe a phenomenon or develop something about which only a little is known.
iii. Snowball sampling. Snowball sampling is the process of selecting a sample using
networks. To start with, a few individuals in a group or organization are selected and
the required information is selected from them. They are then asked to identify other
people in the group or organization and the people selected by them become a part of
the sample. Information is collected from them, and then these people are asked to
identify other members of the group and, in turn, those identified become the basis of
67
further data collection. This process is continued until the required number or a
saturation point has been reached, in terms of the information being sought. This
sampling technique is useful if you know little about the group or organization you
wish to study, as you need only to make contact with a few individuals who can then
direct you to the other members of the group. This method of selecting a sample is
useful for studying communication patterns, decision making and diffusion of
knowledge within a group. There are disadvantages to this technique. The choice of
the entire sample rests upon the choice of individuals at the first stage. If they belong
to a particular faction or have strong bias, the study may be biased. Also, it is difficult
to use this technique when the sample becomes fairly large.
iv. Convenience sampling. This is a sampling method where elements are selected
because they are easily accessible and available. The findings of such a study cannot
be generalized to the population because the elements in the population where not
given an equal chance of being included in the sample.
7.0 Summary
In this unit you have been informed that sampling is the process of selecting a few
from a bigger group. There are three crucial principle of sampling to keep in mind when
undertaking a quantitative research. These principles determine the sample size needed for a
particular level of accuracy and the sampling design best suited for a particular study. Random or
probability sampling designs give all elements in the population an equal chance of being
included in the sample while non – random or non - probability sampling designs not gives all
elements in the population an equal chance of being included in the sample.
68
After reading through unit six, you should answer the question below. It is important
for you to attempt the question in order to gauge how much you have comprehended the material
presented in this unit. If you are having challenges in answering the question, read unit six again.
1. What is sampling? Discuss the three principles of sampling in quantitative research and
the concept of sampling in qualitative research.
2. Explain the following types of sampling designs;
a. Stratified random sampling
b. Proportionate stratified sampling
c. Cluster sampling
d. Purposive sampling
e. Quota sampling
f. Simple random sampling
1.0 Introduction
This unit explains the format for PAS 2014 research proposal. The unit begins by giving an
outline of the research proposal. We will then discuss in detail the each components of the
research proposal.
69
By the end of this unit, you should be able to:
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed,
London: Sage Publications
Grinnel, R. (1995), Research and Evaluation, Illinois: Peacock Publishers
McNabb, D. (2009), Research Methods for Political Science: Quantitative and
Qualitative Methods, New Delhi: PHI Learning Private Limited
It will take you approximately four hours to work through this unit.
All research endeavors in every academic and professional field are preceded by a research
proposal. The research proposal informs other of your conceptualization of the total research
process that you propose to undertake and examine its suitability and validity.
A research proposal is an overall plan, scheme, structure and strategy designed to obtain
answers to the research questions or problems that constitute your research project, Kumar
(2005). A research proposal should outline the various tasks you intend to undertaken to fulfill
your research objectives, test hypotheses or obtain answer to research questions. It should also
state the reason for undertaking your study. The main function of a research proposal is to detail
70
the operational plan for obtaining answers to your research questions. In doing so, it ensures and
reassures others of the validity of the methodology for obtaining answer to your research
questions. Your proposal should follow the suggested guidelines and be written in an academic
style. It must contain appropriate references in the body of the text and bibliography at the end.
In order to achieve this function, a research proposal must provide your readers with the
following information about your study:
Your research proposal for PAS 2014 should contain the following information:
Title
Table of contents
List of Acronyms
CHAPTER ONE
Introduction
Statement of the Problem
Study objectives
Overall objective of the study
Specific of the study
Research questions
Hypothesis to be tested (if applicable)
Definition of concepts / Conceptual framework or theoretical framework
Literature review
CHAPTER TWO
Study design
Study site and study population
Sampling size and sampling design
71
Data collection instruments
Data processing procedure
Problems and Limitations
Ethical issues involved (if any) and how you propose to deal with the research
Bibliography
Appendices
Appendix A: Proposed time frame for the project.
Appendix B: Questionnaire (s)
Appendix C: Interview guide (s)
1. Title
The research proposal should have a title. The title conveys what the research is about. The
title should be expressed in a single sentence and must contain the major construct or action
terms to be used in the research. The research topic is derived from the research problem,
situation or phenomenon that you want to investigate. For example: The relationship between
social environment and the academic achievement. The title should be in bold letters on the
cover page of your proposal.
2. Introduction
The introduction provides a context of the study problem or problem situation. It should start
with a very broad perspective of the main study area before gradually narrowing down to the
central problem under investigation. It should provide specific examples of the nature of the
problem and cite data around the problem. It should give an overview of the of the trends in
terms of prevalence if applicable, the theoretical and practical issues relating to the central
problem under study, theoretical and ideological issues relating to the topic and other relevant
information.( The introduction for your proposal should not exceed three pages). Suppose you
want to study the relationship between social environment and academic achievement. The
introduction would include:
72
Major changes in the philosophy to education.
The development of education in the country.
Trends in education participation in the country with particular reference to the area in
which the study is being carried out.
Role of parents and peers in academic achievement.
Impact of social environment on academic performance.
Etc.
The statement of the problem must describe what is wrong out there which needs to be
investigated. By so doing, you must cite relevant data as evidence to the existence of the
problem. The situation, issue or problem you are investigating should be derived from reality
hence the need for relevant data to support its existence. Having provided a broad introduction to
the area under study, now focus on issues relating to its central theme, identifying some of the
gaps in the existing body of knowledge. Specifically this section should: identify the issues that
are the basis of your study; specify the various aspects of or perspectives on these issues; identify
the main gap(s) in the existing body of knowledge; and raise some of the main research
question(s) that you want to answer through your study.
In a research you have an overall objective which indicates the thrust of the research study
and the specific which identify the specific issues you intend to examine.
Overall Objective
The overall objective clearly states what the researcher wants to investigate. It contains a
relationship of the key variables in the study. The general objective is best stated in a single
sentence.
Specific objectives
73
Specific objectives describe the sub-objectives or specific tasks the researcher intends to carryout
in order to fulfill the overall objective of the study. Specific objectives should be presented using
action oriented verbs.
Examples of objectives
Overall Objective
Specific Objectives
To find out the relationship, if any, between self esteem and a student’s academic
achievement.
To ascertain the association between parental involvement in a student’s studies and
academic achievement.
To examine the link between a student’s peer group and academic achievement.
To explore the relationship between the attitude of a student towards teachers and
academic achievement.
5. Research questions
Research questions guide the research process as they assist in pointing to specific
concerns. The research question should enable you answer the research objectives.
74
A hypothesis is a statement of your assumption about the prevalence of a phenomenon or
about a relationship between two variables that you intend to test within the framework of the
study. If you are going to test hypotheses list them in this section. You must be acquainted with
the correct way of formulating them. In a study, you can have as many hypotheses as you want to
test. However, it is not essential to have a hypothesis in order to undertake a study – you can
conduct a perfectly satisfactory study without formulating a hypothesis.
Example of hypotheses
H1: A student’s self esteem and academic achievement are positively correlated.
H2: The greater the parental involvement in a student’s studies, the higher the academic
achievement.
Under the rationale of the study, you have to outline the value of the research results to intended
users
Under the conceptual or operational definition of concepts, you have to list the concepts
in your study and give an operational definition for each, that is, how these concepts will be used
within the context of your study. The concepts / variables you operationalise are derived from the
research objectives or questions. In the examples of specific objectives, the first one is, to find
out the relationship, if any, between self esteem and a student’s academic achievement. The
researcher should therefore define the concept o self esteem and academic achievement by
stating what they mean within the context of the research and how they will be measured.
The conceptual or theoretical framework which constitutes the basis for your study
should be clearly explained. A conceptual framework is a mental construct of how the variables
are put together to explain the problem under investigation. Through literature review,
observations or experience, you can come up with a conceptualization to explain the dependent
75
variable which represents the research problem. A theory on the other hand is a generalization
which tries to explain reality. There are many theories which can be used to explain various
issues, phenomena or situations. In your research, you either use a conceptual framework or a
theory to explain what you want to investigate.
Literature review is a critical assessment of what others have written about the problem,
situation or phenomenon that you want to investigate. In research, it is important to read and
gather information about the topic so that you are better informed. Literature review enables the
researcher to find out what other have done, prevent unnecessary duplication, provides
convincing arguments on why the research should be undertaken and familiarizes you with
different methodologies that might be useful for your research. Sources of literature include
books, articles, reports, abstracts, indices, research reports, theses/dissertations, databases,
statistical bulletins, newspaper, magazine and other. Literature can be accessed from libraries,
internet, workshops, archives, government departments and other.
When reviewing literature, first state the name(s) of the author(s) , year of publication,
and the title of the publication. Thereafter, explain the major finding, argument or thrust of the
literature (summarise the content of the work relevant to your study) and show its relevance to
your study. Having done that, you should show the gaps in the literature which your study will
fill. Ensure that you repeat this same procedure for every literature that you review. Also see to it
that the literature you review is related to your research. The literature review section for your
PAS 2014 proposal should not be less than ten (10) pages.
The study design describes the plan you intend to use to answer your research questions.
For example say whether it is a case study, cross-sectional, before – and- after or a comparative
study. The research design should also state whether your study will be qualitative, quantitative
or both. You should also mention whether your study will use primary data, secondary data or
both. You should give a justification for every aspect of your study design.
76
Under this section, briefly describe the organization, agency, or community in which you
will conduct your study. If a study is about a group of people, highlight some of the salient
characteristics of the group (such as its history, size, composition and structure) and draw
attention to any available relevant information. If your research concerns an agency, office
organization, include the following in your description; the main services provided by the
agency, office or organization; its administrative structure; the type of clients served; and
information about the issues central to your research. If you are studying a community, briefly
describe some of the main characteristic: the size of the community; a brief social profile of the
community (such as the composition of the various groups within it); and issues relevant to the
central theme of your study.
Sample size is the total number of respondents (people) whom you will ask questions in
order to answer your research questions. Give a detailed explanation of the sampling design that
you are going to use to select your sample and the procedure which you will follow. You should
give a justification of the sample size and sampling design you have chosen.
Data collection instruments refer to the tools which you are going to use to collect
information to answer your research question such as questionnaires, interview guides,
observation forms and others. Explain in detail the tools you will use, why you will use them and
how you will go about collecting the data.
In general terms, describe the strategy you intend to use for data analysis. Specify
whether the data will be analyzed manually or by computer. If data will be analyzed by
computer, state the software which you are going to use. You have to state how the type of data
your research will collect, whether qualitative, quantitative or both will be analyzed.
77
List the possible problems (if any) which may encounter during your study and how you
intend to overcome them.
List the ethical issue issues involved in your study (if any) and how you propose to deal
with them.
Bibliography
List in full all the references which you have used in the proposal. These reference should follow
the alphabetical order of the names of authors cited.
Appendices
Ethics refer to the dos and don’ts or the rights and wrongs of any profession. Ethical
behaviour means behaviour which is accordance with principles of conduct that are considered
correct, especially those of a given type or group. Similarly, research has a code of conduct
which should be adhered to by all researchers. The following are some of the ethical issues to
consider in research:
a. Seeking consent
78
b. Providing incentives
Giving someone an incentive to participate so that they can provide you with the information
that you need for your study is unethical. Money, gifts or presents are not supposed to be given
to solicit for answers from respondents.
Information sought may cause an ethical dilemma in research. Certain types of information
can be regarded as sensitive or confidential by some people and thus an invasion of privacy.
Asking for this information may embarrass or upset a respondent. However, if you do not ask
this information, it may not be possible for you to pursue your interest in the area and contribute
to the existing body of knowledge. It is however not unethical to ask such questions provided
that you tell your respondents the type of information you are going to ask clearly and frankly,
and give them sufficient time to decide if they want to participate.
d. Maintaining confidentiality
Sharing information about a respondent with others for purposes other than research is
unethical. Sometimes you need to identify your study population to put your findings into
context. In such situation, you need to make sure that at least the information provided by
respondents is anonymous. It is unethical to identify an individual respondent. Therefore you
need to ensure that after information has been collected, its source cannot be known.
e. Avoiding bias
Bias on the part of the researcher is unethical. Bias is a deliberate attempt either to hide
what you have found in your study, or to highlight something disproportionately to its true
existence.
79
g. Incorrect reporting
To use an appropriate methodology, but to report the findings in a way that changes or slants
them to serve your own or someone else’s interests is unethical.
7.0 Summary
In this unit you have been informed that a research proposal is an overall plan
designed to obtain answers to research questions. The research proposal for PAS 2014 should
have two chapters. Chapter one consists of the introduction, statement of the problem, objectives,
research questions, hypotheses, conceptual framework / definitions and literature review.
Chapter two is composed of the study design, study site, samples size and sampling design, data
collection instruments and data processing procedure.
After reading through unit seven, you should be able to write a detailed research
proposal in line with the guidance provided in this unit.
REFERENCES
Babbie, E. (1990), Survey Research Methods, 2nd Ed. California: Wadesworth Publishing Co.
Burns, R. (1994), Introduction to Research Methods, 2nd Ed. Melbourne: Longman Cheshire
Hessler, R.(1992), Social Research Methods, New York: West Publishing Co.
80
Kumar, R. (2005), Research Methodology: A Step – by – Step for Beginners, 2nd Ed. London:
Sage Publications
McNabb, D. (2009), Research Methods for Political Science: Quantitative and Qualitative
Nachimias, D. and Nachimias, D. (1996), Research Methods in Social Sciences, 5th Ed.
O’Sullivan, E and Russell, G.(1995), Research Methods in Public Administration, 2nd Ed.
81