Research methods and project (2022) Contact: jeromegerald.jg@gmail.

com/ 0783141929 or
0706513135
Makerere Business Training centre ©
Definitions
Research is a systematic attempt to discover by means of investigation, the laws or principles, which
govern the operation of phenomena. Social Research has been concerned with gathering data that
can help us answer questions about various aspects of society and thereby enabling us to understand
society better.
Stages of Social Research
1. Choosing the Research topic and stating the Hypotheses.
2. Formulating the research design
3. Gathering the Data
4. Coding and analyzing the Data
5. Interpreting the Results

Quantitative Research Vs Qualitative Research

Quantitative means measured or measurable or is concerned by quantity i.e. property of things that is
estimable by some sort of measure, the having of size amount or number. These are aimed at finding
the distribution of the variables among the study populations. Unlike qualitative studies, which
answer the question why, quantitative studies answer how many, how much, how often. In
quantitative studies the sample size is usually big enough and data collection is through tightly
structure closed ended question. Data analysis involves the use of statistical tools and results are
usually conclusive, representative and projectable to the population.

Qualitative Research
Qualitative is concerned with or depending on quality i.e. degree of excellence, relative nature or kind
or character qualitative attributes have labels or names rather than numbers assigned to their
respective categories. The design is mostly used when little is known about the problem under
investigation. The purpose of such a design is to gain and in-depth understanding of the concepts,
variables, of the studies area etc. Data is usually collected using Focus Group Discussion, In-depth
interviews and Observation. Not much statistical analysis is done but rather content analysis is used.
The results are not conclusive and do not represent the entire study populations.

1
 Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
In comparing qualitative and quantitative methods basis will be an objective question, sample size,
sample selection, data collection, instruments and analysis and results.
TERMS QUANTITATIVE QUALITATIVE
1. Sample Size Big Small
2. Sample selection Random procedure Judgmental /purposive key
information

3. Objective Measurement or In-depth Understanding

Quantifying information
4. Questions asked How many, How much Why, how
5. Data collection Questionnaires Focus group discussion, in-
instruments depth, interviews,
observation

6. Data analysis Extensive use of statistical Content /Thematic analysis

methods

7. Results - Conclusive Inconclusive

- Projectable Not Projectable
- Generalisable Not generalisable

Basic Elements of Social Research

a) Concept
This is a mental construct, which selects and summarizes an aspect of the observable world. A concept
is simply any mental image or perception e.g. man, Age. Concepts may be simple or complex.
Examples of complex are intelligence, or democracy. Examples of simple concepts are clan, age, and
sex.
b) Variables
A variable is a concept that takes on more than one value. There two classification of variables
I. The first classification is divided into two
a) Categorical variables: This is when subjects are classified by sorting them out into groups. For
example tribes, religion, residence. The simplest categorical variable has 2 classes and this is
referred to as dichotomous variable for example sex can be classified as male or female
b) Continuous variable: - Is when the attribute has infinite numbers of values within a range for
example weight, age, and height.

2
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
II. The second classification is divided into two
The most important classification of variables is on the basis of their use within research. In this
classification we have independent and dependent variables. Variables that are a consequence of or
that dependent upon antecedent variables are called dependent variables while variables that are
antecedent to the dependent variables are called independent variables. The dependent variables are
the phenomenon that is the object of study or investigation. The independent variable is the factor
that is measurably separate and distinct from the dependent variable.
c) Proposition
Is a statement of relationship between one or more variables. There are three types of propositions.
• A proposition that discusses a single variable is called uni-variate. E.g. Dark people are mean
or 45% of the people in Kampala have used marijuana.
• A bivariate proposition is one that relates two variables e.g. the higher the density level in
city, the higher the crime rate in the city.
• A proposition that relates more than 2 variables is called multivariate e.g. the higher the
density, the higher the rates of illiteracy and drug addiction.
d) Hypothesis
A hypothesis is a proposition that is stated in a testable form and predicts a particular relationship
between two or more variables or Hypothesis can be defined as a tentative propositions or statement
suggested as a solution to a problem or as an explanation of some phenomenon. The hypothesis must
be formulated before the actual data collection phase for two reasons
i) A well-grounded hypothesis indicates that the researcher has sufficient knowledge in the area
to undertake the investigation
ii) ii) The hypothesis gives a direction to the collection and interpretation of the data i.e. tells
what procedure to follow and the type of data to gather.

Types of Hypothesis:
There are two types i.e. the research and Null hypothesis
i) Research/Alternate hypothesis
Research Hypotheses are those developed from observation, related literature and or the theory
described in the study. They refer to statements about the relationship one expects to find of the
research e.g. mothers who have lost children during infancy have a positive attitude towards
immunization.

3
 Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
ii) Null hypothesis
A null hypothesis states that there is no relationship or difference between variables and that any
relationship found will be a chance relationship rather than a true one. Null hypothesis are usually
used because they suit statistical techniques, which determine whether an observed relationship is a
chance or a true relationship.

Measurement
Measurement is assigning numerical values to objects or events or their characteristics according to
conventional rules. When we do research, we assign numbers to different sizes quantities, or qualities
of the events under observation. We are all familiar with such conventional physical dimensions as
length, width and height. Rather than relying on global impressions (it is really ―big or ―far), we
use standardized units, agreed – upon conventions that define such measures as the minute, the meter,
and kilos.
Levels (Types) of measurement
The level of measurement is the kind of scale used to measure a variable. There are four levels of
measurement namely: - nominal, ordinal, interval and ratio.
1. Nominal Scale
This is the simplest level of measurement, which classifies items into two or more distinct categories
on the basis of some common feature. A nominal scale groups’ items together into categories that can
be named (the term nominal from the Latin word for ―name‖). But it does not quantify the items in
any way. Nominal scaling is sometimes called the lowest level of measurement because it provides
no information about magnitude.
For example sex – male or female, Political affiliation – UPC, Movement, DP, Football Numbers- 1,
20, 31
The numbers assigned to the categories do not have any mathematical or statistical functions.
2. Ordinal Scale.
This is the second level of measurement. It has the properties of the nominal measurement and is a
rank ordering of items. The magnitude of each value is measured in the form of ranks. The categories
at this level are characterized by one category being bigger or higher or more desirable than another.
For example: - Level of education- Primary, secondary, & tertiary, Socio economic status: - Upper
Class, Middle Class and Lower Class
3. Interval Scale
This has the properties of nominal and ordinal levels. It measures magnitude or quantitative size using
measures with equal interval between the values. However, an interval scale has no true zero points.
For example: - temperature, time.
4
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
4. Ratio Scale
It has properties of the nominal, ordinal and interval scale. This is the highest level of measurement,
which has equal intervals between all values, and a true zero point measures of physical properties
such as height and weight are variables whose quantity or magnitude can be measured using ratio
scale.
SOURCES OF ERRORS IN MEASUREMENT
a) Respondent: At times the respondent may be reluctant to express strong negative feelings or it
is just possible that he may have very little knowledge but may not admit his ignorance.

All this reluctance is likely to result in an interview of ‘guesses.’ Transient factors like fatigue,
boredom, anxiety, etc. may limit the ability of the respondent to respond accurately and fully.

(b) Situation: Situational factors may also come in the way of correct measurement. Any
condition which places a strain on interview can have serious effects on the interviewer respondent
rapport. For instance, if someone else is present, he can distort responses by joining in or merely by
being present. If the respondent feels that anonymity is not assured, he may be reluctant to express
certain feelings.

(c) Measurer: The interviewer can distort responses by rewording or reordering questions. His
behavior, style and looks may encourage or discourage certain replies from respondents. Careless
mechanical processing may distort the findings. Errors may also creep in because of incorrect
coding, faulty tabulation and/or statistical calculations, particularly in the data analysis stage.

(d) Instrument: Error may arise because of the defective measuring instrument. The use of
complex words, beyond the comprehension of the respondent, ambiguous meanings, poor printing,
inadequate space for replies, response choice omissions, etc. are a few things that make the
measuring instrument defective and may result in measurement errors. Another type of instrument
deficiency is the poor sampling of the universe of items of concern.

NB! Researcher must know that correct measurement depends on successfully meeting all of the
problems listed above. He must, to the extent possible, try to eliminate, neutralize or otherwise
deal with all the possible sources of error so that the final results may not be contaminated.

Tests of sound measurement

Sound measurement must meet the tests of validity, reliability and practicality. In fact, these are the
three major considerations one should use in evaluating a measurement tool. “Validity refers to the
extent to which a test measures what we actually wish to measure. Reliability has to do with the
accuracy and precision of a measurement procedure ... Practicality is concerned with a wide range

5
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
of factors of economy, convenience, and interpretability ...” We briefly take up the relevant details
concerning these tests of sound measurement.

1. Test of Validity
Validity is the most critical criterion and indicates the degree to which an instrument measures what
it is supposed to measure. Validity can also be thought of as utility. In other words, validity is the
extent to which differences found with a measuring instrument reflect true differences among those
being tested.

2. Test of Reliability
The test of reliability is another important test of sound measurement. A measuring instrument is
reliable if it provides consistent results. Reliable measuring instrument does contribute to validity,
but a reliable instrument need not be a valid instrument. For instance, a scale that consistently
overweighs objects by five kgs., is a reliable scale, but it does not give a valid measure of weight.
But the other way is not true i.e., a valid instrument is always reliable. Accordingly reliability is not
as valuable as validity, but it is easier to assess reliability in comparison to validity. For example a
test re-test reliability.

Research Designs
1. Descriptive Research Design
This involves a systematic collection and presentation of data to give a clear picture of a particular
situation. There are three types of descriptive research designs: -
a) Census
This is the complete enumeration of a population or group at a point in time with respect to well
defined characteristics. A census is a study, which includes 100 per cent of the population. A
population census is the collection analysis of basic, social demographic and economic data for the
entire population of a country.
b) Surveys
These are relatively extensive and wide studies. They use interview or self-administered
questionnaire as methods of data collection. They aim at quantifying the distribution of certain
variables in a study population.
c) Case studies
These investigate or examine in detail relatively few persons or items for examples one person, one
health centre or a village. Such studies not only do they produce information on behavior and practices
but also underlying ideas and beliefs.

6
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
2. Correlation Research Design
This attempt to determine whether and to what degree a relationship exists between two or more
quantifiable variables. The purpose of a correlational study is to establish a relationship or lack of it
or to use the relationship in making predictions.
3. Comparative Research Design
Comparison is a fundamental research strategy to identify factors that explain why one group of
persons or objects differs from another. Such a design provides a stronger basis for analysis than one
involving only one group. In comparative research design the research compares one group with the
problem, with another that as no problem.
There are two types of comparative studies or designs.
a) Case control
In case control the researcher compares one study group among whom the problem is present with
another group (control or comparison group where the problem is absent. In studying the two groups
the researcher will try to identify factors that are associated with the problem.
In case control studies one starts with the out come and then looks back to determine the presence or
absence of these associated factors. This is called a retrospective study design.

b) Cohort study
In a cohort study a group of individual that are exposed to a risk factor are compared with a group of
individuals who are not exposed to the risk factor and the researcher follows both groups overtime to
compare the occurrences of the problem. This is called a prospective study design

II. SAMPLING
Introduction:
• A sample is a part of the population, which is deliberately selected for the purpose of
investigating the properties of the parent population
• A population is the complete set of individual objects or measurements having common
observable characteristics
• Elements or Subjects are individuals or units about or from whom information is collected.
• A parameter is any characteristic of a population, which is measurable or observable.
• A statistic is any characteristic of a sample, which is measurable.
In research, with the exception of a complete census, data is collected from samples and then the
research findings are generalized to the population from which the samples are selected.
This means that researchers measure statistics and generalize to get/estimate the parameters.

Reasons for sampling;

7
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
1. Economical
2. It requires fewer researchers, or research assistants.
3. When few assistants are used, the investigator chooses the best qualified than when many are
needed.

4. Ensures quality than when many research assistants are used

5. Time saving: Studies which have many elements may take a long time to be conducted and
when they are completed, it is difficult to specify the time to which the data refers, and the
phenomena being studied may change

6. It has reliability because it’s based on probability theory

Disadvantages or limitations of sampling

1. Scope of biasness. (Less accuracy)

2. Problem of representative sample-Difficulty in selecting a truly representative sample.
3. Need of eligible researchers.
4. Instability of sample subjects or changeability of units i.e. in heterogeneous population.
5. There are certain situations where sampling is possible.

Causes of incorrect inferences

1. Systematic bias/non sampling error

2. Sampling error
A systematic bias/Non sampling error results from errors in the sampling procedures, data
collection methods and analysis. However, they cannot be reduced or eliminated by increasing the
sample size. At best the causes responsible for these errors can be detected and corrected. Usually
a systematic bias is the result of one or more of the following factors:

a) Inappropriate sampling frame: If the sampling frame is inappropriate i.e., a biased

representation of the universe, it will result in a systematic bias.

b) Defective measuring device: If the measuring device is constantly in error, it will result in
systematic bias.
c) Non-respondents: If we are unable to sample all the individuals initially included in the
sample, there may arise a systematic bias.

8
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
d) Indeterminacy principle: Sometimes we find that individuals act differently when kept

under observation than what they do when kept in non-observed situations.

e) Natural bias in the reporting of data: People in general understate their incomes if asked
about it for tax purposes, but they overstate the same if asked for social status or their
affluence. Generally in psychological surveys, people tend to give what they think is the
‘correct’ answer rather than revealing their true feelings.

Sampling Errors
These are errors made when the characteristics of a population are estimated with the samples instead
of the population. Errors due to the improper selection of the samples, due to faulty methods of
collecting and analyzing the data are called non-sampling errors. Sampling errors are a function of 2
factors
1. Homogeneity of the population
If the population is completely homogeneous no sampling error can be made. The more homogeneous
a population is, the smaller the sampling errors which can be made
2. Sampling size
The larger the sample selected the smaller are the sampling errors made in research.

Sample size (Homogeneity)

100

75
50
25
0 2550 75 100
Sampling error

Sampling Techniques:
Sampling techniques are mechanisms used to select a sample. These are divided into two broad
categories. The random or probable and the non-random or non-probable or judgmental sampling
techniques. In the random sampling techniques every element in the population has a calculable or
non-zero chance of being included in the sample. On the other hand, in the non-random techniques
the elements are selected without the element of randomness and are based on the personal judgment
of the researcher.

Random Sampling Techniques

The common random sampling techniques are

9
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
a) Simple Random Sampling
This is the simplest technique and is more basic than the others techniques. Every element has an
equal chance of being selected in the sample. There are two methods in simple random sampling:
i) The Lottery Method
In lottery method, the names of the elements of the populations are listed and numbered (sampling
frame) then the names or numbers of the names are written on pieces of paper and put into a container
and mixed thoroughly. A blind folded individual picks one piece of paper at a time. Whoever is picked
is included in the sample. After each picking, the pieces are mixed again. The selection can be done
with replacement or without.
ii) Random Table Method
In this method tables of random numbers are used. Random numbers are numbers generated by
computers in such a way that each number has equal probability of being selected. These numbers
may be any figures but are usually two or four or five, digit numbers. The table can be read vertically
or horizontally from left to right or from right to left. The elements of the population are listed and
numbered then we refer to the random numbers and decide randomly whether to read it vertically or
horizontally (e.g. tossing a coin) we could use the lottery method where by the less columns or rows
are written on pieces of paper. Then we start selecting numbers column after column until we have
the required sample size.
For example:
23 65 98 74 15 61

03 24 09 35 37 24

14 99 82 31 54 68

26 53 33 55 82 91

88 20 30 56 10 11

50 19 51 05 06 18

b) Systematic Random Sampling

In systematic random sampling the elements are listed and numbered. A sampling fraction is obtained
by dividing the population size by the sample size. The answer obtained is called the sampling interval
(if it is not a whole number, it should be approximated to the nearest whole number). For example if
we have a class whose population is 160 we want to use systematic ransom sampling to select 40
students we find the sampling fraction and the sampling interval 160/40 = 4. The sampling interval

10
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
th
of 4 means that every 4 element is selected so we randomly select an element between 1-4 then we
add keep on adding 4 until we get 40 people
Assuming 2 is selected
2 + 4 = 6, 6 + 4 = 10, 10 + 4 = 14
Systematic random sampling is used under the same conditions as sample random sampling that is
when the population is small, relatively homogenous not to require stratification and when a sampling
frame is available. It is often preferred to the simple random sampling because the selection is often
spread throughout the population.

c) Stratified Random Sampling

In this case the population is divided into groups called strata (singular is stratum) and the elements
are randomly selected from each of the stratum. The stratification factors must be related to the study.
Sex, education level, socio-economic status religions are common stratification factors. The elements
in the strata should be as homogenous as possible. This reduces the sampling errors because variation
between the strata is not incorporated in the calculation of the sampling errors. In selecting
proportional stratified samples, the population size of each strata is multiplied by the required (total)
sample size and divided by the total population.
(Total sample size) X (total population in a stratum)
Total population
The total population in boy‘s halls of residence is 3000 and let‘s assumes that the required total sample
is 600
HALLS POPULATION SAMPLE
North 650
Nkrumah 450
Livingstone 350
Lumumba 500
University 650
Mitchell 400
Total 3000

Proportionate and Disproportionate Stratified Sampling

In proportionate stratified sampling, the size in each stratum is proportional to the total number of
elements in the stratum. Most stratification designs are proportionate and called proportional probable

11
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
sampling. Due to a number of factors, some strata may be under sampled where as others may be
over sampled. This is called disproportionate probable sampling.

d) Multi stage stratified sampling

If the strata of a population can be hierarchically arranged then the population can then be stratified
at different levels. The first level of stratification is called the primary sampling unit (PSU). The
second and third levels are called the secondary sampling unit (SSU) and the tertiary sampling unit
(TSU) respectively. The level at which the elements are randomly selected is called the ultimate
sampling unit (USU). In most research stratification stops at the secondary sampling unit (SSU), for
example in the study of book allowance, the primary sampling unit may be faculties/institutes and the
secondary sampling unit may be the year of study and then the research can obtain sampling frames
from the respective deans.
In study investigating the food served in halls of residence PSU may be halls, the SSU – year of study
and TSU may be sex or tribe or religion. Multistage stratified sampling is employed for the same
reasons as the stratified sampling. The multi stage sampling has an additional advantage in that the
different levels of stratification (i.e. PSU, SSU) can be the domains of study.
e) Cluster sampling
A cluster is a unit of a naturally intact group with similar characteristics. A cluster sample is a random
sample in which each sampling unit is a collection or cluster. In cluster sampling, the population is
divided into groups and some of the groups are sampled. Clustering may be either single stage or
multi stage. In single stage clustering, after the selection of the clusters others every element in the
cluster is included in the sample (this is called complete coverage) or the elements in the sampled
clusters are listed, numbered and a random sample of them is selected. In multi stage cluster sampling,
clusters are selected and from these selected clusters, inner clusters are selected e.g. for districts to
sub counties

Non-Random sampling techniques

In the non-random sampling techniques there are no sampling frames required. The selection is based
on the researchers’ knowledge of the population and on the aim of the study. The common non-
random sampling techniques are: -
a) Accidental Sampling
In accidental sampling, any element, which is part of the population and happens to be within reach
of the researcher, is included in the sample. The weakness of the techniques is that the sample selected
rarely representative of the population. But if the phenomenon studied is rapidly changing then

12
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
accidental sampling may be most appropriate because there is no time to construct the sampling
frame.

b) Snowball Sampling
In snowball the investigation identifies a few individuals who participate in secretive behaviors (e.g.
drug taking, abortion). Then he wins the confidence of those few and they refer more cases to him
The snowball sample may not be representative but it‘s the most appropriate technique to select
samples to study secretive behavior.

c) Quota Sampling
The population is divided into groups or strata according to the important characteristic of the
population in quota sampling, stratification factors are called controls e.g. age, sex, religion. The
number in each stratum is called a quota. After the number in each quota has been set, the interviewer
selects and interviewee’s respondents who belong to the quotas until the quotas are filled. Quota
sampling is therefore a method of stratified sampling in which the selection within the strata is not
random. The sample in any particular stratum is an accidental sample of the corresponding stratum
of the population.

Comparison between Random and Non-Random Sampling

a) In the random selection, the sampling errors can be estimated while in the non random
this error cannot be estimated unless replicated methods are used. (Many samples are used
and the differences between the various estimates are a measure of the sampling error).
b) In random Selection, every element has an equal chance of being selected while in the
non-random selection, participation of an element is determined by the interviewer.
c) Random selection technique use a sampling frame while non – random techniques no
sampling frame is needed
d) The non-random techniques are often less costly than the random. The random are
more costly because the interviewers have to trace and track pre- selected respondents and
make at least four calls.

III. QUESTIONNAIRE CONSTRUCTION:

A series of related questions asked to individuals to obtain statistically useful information about a
given topic. In questionnaire construction, the researcher should focus on the variables and break
them down until one sieves out clear meaning and reach at what you want out of the study for
example, what comprises of roommate satisfaction? List all the options and it’s from those that
you build own questions not losing sight of the concept in question.

13
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©

Examples of different scales

1. Multiple choice. A question with several response options (typically four to five) is provided
and respondents select a single response e.g. when are you most likely to confide something
personal to your roommate?
o When I have a problem and need advice
o When something good has happened
o When I have a secret I want to share
o Never

2. Dichotomous. A statement with two responses such as YES/NO, True or False

3. Checklist. Provide a question with several options and direct respondents to check all that apply
e.g. I talk to my roommate about personal matters when (please select all that apply)
o I need to confide in someone
o I need to ask advice
o I want to share good news
o Never
4. Rating scale. Provide a statement/question with response options on a continuum and instruct
respondents to select a single response. E.g. When I have a problem, I greatly value the advice
of my roommate.
o Strongly agree
o Somewhat agree
o Neutral
o Somewhat disagree
o Strongly disagree

NB! Response choices must be mutually exclusive and exhaustive. Mutually exclusive means that
there’s no overlap in response items and exhaustive means that all of the possible responses a
respondent might wish to select are available. E.g. My roommate makes his/her bed
o 1-2 times per week
o 2-3 times per week
o 4-5 times per week Not mutually exclusive
o 6-7 times per week
o Never
14
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
OR
o 1-2 times per week
o 3-4 times per week Not exhaustive
o 5-6 times per week
o 7 days

Note! Create a respondent inventory also called a respondent audit. In order to keep track of
respondents and reduce the risk of multiple responses from one individual (Ruel et al, 2016) Each
respondent can be assigned a number for anonymity.
Questionnaires
There are three types of questionnaires
1. Self-administered questionnaire
This is a predetermined written list of questions, which may be answered by a respondent
without supervision or explanation. Questionnaires are used in self-administered research
and are either sent in the mail or at home or office delivered. They can also be administered
to a group.
2. An Interview Schedule or a Response Schedule is a predetermined set of questions
and instructions intended to standardize the interview procedures. The questions are
asked and the answers recorded in a set order and with only the allowed probes or
explanations.
The response schedule is used in the formal or structured interview
3. Interview guide is a set of topics and or questions about which the interview is
conducted. The order and the number of the questions and the topics are determined
by the interviewer, depending on how knowledgeable or informative the respondent
is about the interview.
The principles, which guide questionnaire construction include: -
1. Overall Principles
In designing a questionnaire, the researcher should know the goal and the specific aims and objectives
of the study. He should know the method, which will be used in collecting the data (interviews,
telephone, group-administration, participant observation etc). The hypothesis, the independent and
dependent variable and the methods of analyzing the data should be known, for example one should
know whether the data will be content analyzed, the researcher should know the computer program.
He/she should anticipate most of the tables, which will be formulated and should construct these
tables. These tables are called dummy tables. These tables enable the researcher to make sure that all

15
 Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
the required independent variables are included. They also help the researcher to make sure that all
the information required to test the formulated hypothesis will be collected.
2. Question Content
It’s important for the designer to ask oneself whether the respondents are likely to possess the
knowledge or have access to the information necessary to answer the questions. The designer
should know whether the question designed is a factual or an opinion or a knowledge question.
a) Factual questions
Questions which have an exact answer or whose answers can be confirmed or validated are known as
factual questions. These questions can be confirmed by either observation or by consulting
documents, e.g. sex, age. Factual questions are not dependant on wording of the question or the tone
of asking. These questions classify the respondents into different, tribes, different religious
affiliations, and different socio – economic status. They are therefore known as classification
questions.
b) Opinion Questions
These do not have an exact or ―correct‖ or conformable answer. They are characterized by
i. Degrees of Saliency:
For factual question either the respondent knows the answer or he does not (e.g. he either knows
that he has a watch or he doesn’t) but for opinion questions the respondent might have never thought
of the answer. Some respondents have a clean, fixed, concise answer where as others need self –
analysis before they can answer the questions.
ii. Different Perspectives:
Opinions questions can be answered from different point of view/perspectives e.g. whether abortion
should be legalized religious perspective, medical, psychological, socio-economic point of view etc.
The answer given depends on the perspective adopted.
iii. Different Intensities
Some respondents feel very strongly about their opinions while others are undecided e.g. political
parties.
iv. Sensitivity to changes in words, Emphasis and sequence
Since opinion questions can be answered from different perspectives, different words or different
emphasis or sequences might tap different perspective from which the question will be answered.
3. Question Wording
As we construct a questionnaire, we pay particular attention to the wording we use. The wording
should be as simple as possible. Technical terms, jargons and slang should be avoided. If a research

16
 Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
is being conducted in Vernacular, the questionnaire should be drafted in English, then translated in
vernacular by an expert of the given Vernacular and then re-translated back into English

a) Ambiguous questions, should be avoided because they encourage ambiguous

answers. This is due to the fact that the question is asking two questions in one. For example:
Are you satisfied with the lecturer and hours of lectures?

b) Leading questions / loaded questions Are questions in which the respondent is

answers the question from the interviewer or research point of view. A question might be
leading because of the wording, the structure, the context and tone. Example: In Uganda, a
lot of people have been victimized because of their party affiliations, should we not have a
one party system? For such a question most respondents are likely to agree.

c) Presumed Questions. It is a question, which assumes that the respondent engages in certain
activities or possesses certain opinions or attitudes e.g. how many cigarettes do you smoke at day
Presumed questions should be preceded with filter questions e.g. Do you smoke?

d) Hypothetical Questions. This is a question, which requests the respondent to put himself in
the shoes of other people or to imagine a situation and answer from that imagined situation.

e) Embarrassing questions. These are ones whose answers are of low prestige. Most of these are
likely to be answered in such a way that the respondent appears ―normal‖.

4. Open ended Questions and Pre-Coded Questions (Closed Ended Questions)

When constructing a questionnaire we decide whether to ask an open ended or pre-coded questions.
The open is asked in such a way that the respondent is allowed to decide the aspect, form, detail and
length of his answer. For pre-coded question, the questions have answers attached to them and the
respondent chooses one of these attachments.

5. Question Order
As we group the questions together they should have a particular order because the order of the
questions has been found to influence the response rate and non-willingness to participate. Questions
should be arranged in such a way that we begin with the easy ones first. This helps the respondent
gain confidence and establishes rapport. Sensitive and personal questions should be kept at the end
of the questionnaire because then it is less likely for the respondent to discontinue with the interview.

17
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
6. Pre – tests and Pilot Studies
An essential component of questionnaire construction are pre – tests and pilot studies. After the
questionnaire has been constructed it must be pre-tested and pilot tested because although the
designer of the questionnaire might have tried to follow the principles he has to find out which
questions are vague, ambiguous and reaching. In pre testing and pilot testing the questionnaire, a
sample comparable to the population of the survey is selected and the questionnaire is administered
to their sample. The goal to find out whether the questions are interpreted correctly and whether the
spaces provided for the open questions are adequate.

7. Instructions in the Questionnaires

Self-administered questions are and response schedule contain instructions. In the former the
instructions are addressed to the respondents and in the latter they are addressed both to the
interviewer and respondents There are two types of instructors
1. General Instructions
2. Specific Instructions
The general instructions may include: - who to interview, how many calls have to be made what to
do when a respondent does not respond adequately or gives a wrong answer, where to include the
additional information and when to include. The specific instructions are related to the questions.
These are usually skip instructions for example if question 9 is not applicable skip and go to question
14. They may also include probe instructions.

IV. METHODS OF DATA COLLECTION

There are five methods of collecting the data
These are
1. Interview
2. Self-administration questionnaire
3. Observation
4. Experimentation
5. Document Analysis
1. Interview
An interview can be defined as a face-to-face conversation between an interviewer and a respondent
conducted to obtain information from respondent.
There are two types of interviews:-
1. In the formal interviews each respondent is asked the same questions in exactly the same order.
The sequence and the wording of the questions are worked out before hand and are

18
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
standardized through pretests and pilot tests. The answers are recorded verbatim (this means
word for word)
2. In informal interview, there are no set questions only a number of key points around which
the interview is built, the depth the extent and the wording of the questions are tailored to the
respondent. The more knowledgeable and informative the respondent is, the more detailed
questioned he is.
Tasks of the Interviewer
These include:-
a) Locate the respondents
This depends on the sampling design. If it is random selection the respondent is pre-selected the
interviewer has to look for the pre-selected respondent. If the respondent is not available, the
interviewer has to make four calls before the interview can be ascertained that the pre-selected
respondent will not participate in the study and then he replaces him or her with one from the reserve
list. If the selection is non-random then whoever the researcher bumps into and is part of the
population, is included in the sample.
b) Obtain the Interview
Having located the respondent, the interviewer has to obtain the interview. The introduction must aim
at increasing the respondents’ motivation to participate. This is usually done by interviewer
introducing himself, the organization which he is working for. The interviewer has to explain the
objectives of the study, who is sponsoring; He should further explain how the respondent was selected
and that the answers which the respondents give will be confidential and anonymous.
c) Asking Questions
In formal interviews, the aim is to obtain uniformity in asking questions and recording the answers.
The interviews are expected to ask all applicable questions, to ask them in the order given and to
make no unauthorized variation in the wording. An important part of the interviewer task is to assess
the adequacy of the responses and where necessary probe for further information.
There are 5 principal ways of recognizing inadequate responses
• Partial Response: The respondent gives a relevant but incomplete answer.
• Non-response: The respondent remains silent and refuses to answer the question.
• Irrelevant Response: The respondent does not answer the question asked.
• Inaccurate response: The reply is biased and distorted.
• Verbalized Response: The respondent explains why he cannot answer the question.
A probe is a device which is used to elicit adequate answers from the respondents and to structure
and direct the interviews.

19
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
Probes serve two functions
1. They lead the respondent to answer more fully and accurately.
2. They structure the respondent’s answer and make sure that all topics of interest to the
interviewer are covered and the amount of irrelevant information is reduced.
There are five types of probes:-
1. Repeating the Question
This is done whenever the respondent hesitates or appears not to understand the question.
Length questions are often repeated twice before the respondent has it clearly enough in mind.
2. Repeating the answer.
This can be used by the interviewer who is not certain that he or she understood the
respondent’s answer correctly. This corrects errors and assures both the respondents and the
interviewer that the answer is recorded correctly. It also gives the respondent an opportunity
to think about elaborating the answer further.
3. Indicating Understanding and interest
The interviewer indicates that he or she has heard the answer and approves of it, thus
stimulates the respondent to continue, for example words such as ― I see‖, ―I understand‖.
4. Pause or Silence
The interviewer pauses and says nothing if the response is obviously incomplete. This
indicates that the interviewer knows the respondent has begun to answer and is waiting for
him or her to finish.
5. A neutral question or comment
This indicates to the respondent that the interviewer is interested in what the respondent is
saying but that more information is required.
E.g. what do you mean, tell me more about it, can you explain a little more, why do you feel
it‘s like that?
Example:
Qn: What do you think are the most important problems that we have in Uganda Today?
1. Answer: High taxes
a) Silence or pause to wait for the respondent to continue
b) Repeat the question
c) That‘s one what are the others.
2. Answer: Governmental problems (Answer is vague)
a) I‘m not quite sure I understand what you mean.
b) What kind of governmental problems

20
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
c) Could you be more specific
d) Recording the answers
For pre-coded questions, the interviewer has to decide on the appropriate code and ring or circle it as
instructed. For open-ended questions, the interviewer has to record the answer verbatim. i.e. word
for word. He or she may use abbreviations. Tape recording the interview has the advantage of
relieving the interviewer of the burden of recording but its expensive to use (dry cells, tapes)
experience technical problems need to transcribing.
e) Editing
Towards the end of the interview, the interviewer should edit it by going over the response schedule
and making sure that all applicable questions have been asked and that all the answers have been
recorded. If there are any inconsistent answers, the inconsistency should be solved or ascertained. The
interviewer should briefly describe the environment, the mood and should assess the validity of the
answers he/she should later make sure that personal symbols, abbreviations are written out in full.

Selection of interviewers
The personnel selected as interviewers are important in the collection of the data because the
reliability of the data depends on them. Although researchers don’t agree on the characteristics, which
make an interviewer to be successful, the following are the most important.
a) Honesty: Interviewers should be honest and trustworthy; they should be honest to follow the
sampling and interview instructions and not to fabricate partially or wholly the interviews.
b) Accuracy: Interviewers should be accurate in recording the data, in following instructions and
reading questions.
c) Interest: Interviewers should be interested in their work because errors and poor-quality work
are more likely to occur if the interviewer gets bored and regards the work as valueless.
d) Adaptability: Interviewers should be adaptable to the field conditions of working alone and
sometimes in rural areas, which may not have the city kind of life.
e) Personality: The interviewer’s manner should be friendly, courteous and unbiased he should
be conventional likeable and able to develop a rapport between himself and the respondent.
f) Intelligence and Education: The interviewers should be intelligent and educated enough to
understand and follow instructions and should be knowledgeable in the subject matter of the
survey.
g) Lastly the interviewers should belong to the locality of the survey and should be fluent
speakers of the survey language and should also know the cultural norms.

21
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
ADVANTAGE OF INTERVIEWS
1) One of the most important advantages of interview as a method of data collection is that it can
be adapted to collect generalizable information from almost any known human population.
2) Interview is the most appropriate method used to study attitudes, values, beliefs and motives
of the respondents.
3) Interviews are more structured and more standardized than other methods. Because of this
standardization it is a more efficient method of collecting data.
4) Interviews are flexible; the interviewer can probe for more specific answers. He can repeat
the question when the responses indicate that the respondent misunderstood the questions.
5) An interview allows the assessment of non-verbal behavior such as facial expressions. The
interviewer can also assess the reliability and the validity of the respondent’s answers.
6) With the interview method it‘s possible to make sure that all applicable questions have been
answered by the respondent and the interviewer can edit the interview. In mail, questions
applicable to the respondent may remain unanswered and editing is not possible.

DISADVANTAGES OF INTERVIEWS
1 One of the disadvantages of interviews is that they often costly. The larger the sample, the
more complex the study and the more are the expenses incurred
2 Many of the interview studies are lengthy. The questionnaire has to be made, pre-tested and
pilot tested and if the respondents are not readily available at the place of the interview four
calls have to be made.
3 The interaction between the interviewer and the respondent is sometimes a source of interview
errors and biases and also a source of respondent‘s errors. The interviewers and the
respondents‘ sex, age, race, social class and physical appearance are some of the factors which
may bring about the biases and errors.
4 The fourth disadvantage is that the interviewer‘s method does not allow the respondent to
check records, or to consult friends. For some research more informative and valid data is
collected if the respondent is allowed time for consultations and to think over questions and
formulate the answers.
2. Mail questionnaires
A self-administered questionnaire or mail questionnaire is a predetermined written list of questions
which may be answered by a respondent without supervision or explanation by the interviewer. The
questionnaire is either sent through the post office or is delivered to the homes or offices of the

22
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
respondents. They are either sent back through the post or can be fetched by the researcher. Due to
its infrequent use, mail questionnaires are likely to remain a textbook method for some time.
Advantages of Mail Questionnaires
1) Mail questionnaire is generally cheaper than other methods of data collection. If the postal
charges incurred in posting the questionnaires are compared to the salaries of the supervisors
and of the salaries of the interviewer it‘s for cheaper to use mail.
2) The mail questionnaire avoids the problems associated with the use of interviews i.e. Response
errors (The difference between the individuals true value and the answer recorded). These
errors sometimes seriously undermine the reliability and validity of the data.
3) If the research requires consultation of either documents or with people, the mail questionnaire
is more appropriate than the interview for instance if its type of treatment offered in a hospital,
the respondent may need to consult with the records of the hospital.
4) There is evidence that some people answer personal and embarrassing questions more
willingly and more accurately when they are not face to face with an interviewer. Respondents
make more critical comments and report the less socially acceptable responses more readily
on a mails questionnaire.
5) The mail questionnaire avoids the problems of non – contact and call backs which are often
done in interviews.
Disadvantages of mail questionnaires
1. Non response
The main problem with mail surveys is that of getting inadequate response rate. The response rate of
mail questionnaires is often much lower than that of interview surveys. Therefore, steps must be taken
to increase the response rate by manipulating the variables which affect the response rate. These
include: - the sponsor, the survey population, pilot studies, and covering letters.
a) Sponsorship: The organization under which the research is conducted has been found to affect
the response rate if the organization sponsoring the study is well known as a responsible group,
the response is likely to be good, for instance Ministry of Health & Ministry of Education Vs
Ministry of Finance.
b) Survey population: while sponsorship can be manipulated the survey population cannot.
However, it should be noted that the less educated, those in lower occupational categories and
those who are uninterested in the subject are more likely not to respond.
c) Pilot Studies: These are needed more in researches conducted by mail questionnaires than those
conducted with interviews. Since there are no interviewers to explain, or interpret the
instructions to clarify the vague and ambiguous words or questions pilot studies can be used

23
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
on experimental basis to try out different covering letters, different formats & the
questionnaires etc. and see which one will increase the response rate.
d) Covering letters: These are very important in mail question because there is no interviewer to
introduce the research. The letter should not promise anything of material or social benefit.

2. The method can only be used if the questions are sufficiently simple and straightforward to
be understood with the help of printed instructions and definitions. However, the high rates of
illiteracy which probably vary from about 30 percent to 70% in the developing countries rule
out mail questions as a method of data collection
3. The answers to mails questionnaire have to be accepted as final. There is no interviewer to
probe when the answers are vague, meaningless, irrelevant and contradictory.
4. A mail questionnaire is inappropriate where spontaneous answers are needed, and where it‘s
important that the views of one person only are obtained uninfluenced by discussion by others.
5. The research cannot be sure that the person selected to participate in the study to the one who
completed the questionnaire.
6. There is no opportunity to supplement the respondent’s answers with observation.

3. Observation
Observation is the purposive or intentional examination of something particularly for purpose of
gathering data. The observational method is the primary technique for collecting data on non-verbal
behavior. Although observation most commonly involves sight or visual data collection, it could also
include data collection via the other senses such as hearing, tasting, touch or smell. Observation is
preferred when one wants to study in detail the behavior that occurs in some particular setting or
institution.
There are two main types of observation
1. Non participant Observation
A non-participant observer does not participate when in-group activities and does not pretend to be a
member
2. Participant Observation
The participant observer is a regular participant in the activity/ies being observed and his or her dual
role is generally not known to the other participants.
Advantages of Observations
1. The greatest advantage of observation is that it enables the researcher to study behavior as it
occurs. When the research techniques of interview, mail and document analysis are used to

24
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
study the behavior of people, the researcher depends on their retrospective reports. Often there
is a discrepancy between the reported behavior and the actual behavior.
2. The second advantage of observation is that it is the only method which can be used it the
informant cannot express himself meaningfully. For instance children, the very sick, groups
like mobs or riots.
3. If the individuals are not willing to be interviewed or to fill in questionnaires, they could be
studied using observation. The method does not necessarily need the co-operation of those
being studied. However this undermines ethical issues i.e. people should not be studied
without their consent.
4. The researcher can adjust the goals and objectives of the study as the data is collected. This
open-endedness of observation is not applicable in interview or mail where the objectives of
the study can only be adjusted during the pilot studies after which the objectives are fixed.
5. The fifth advantage is that observation is free of response errors. These errors arise from the
interview or questionnaire situations.
6. Observation method usually provides a richer and more direct account of the phenomena
under study since behavior is taking place in its natural environment.

Disadvantages of Observation
1. The researcher has to wait until the phenomena or event to be observed occurs. If for instance
you want to study circumcision you have to wait for the season or time for these ceremonious
rituals.
2. It is difficulty to have random and representative samples. These are needed if the research
and findings are to be generalized. In theory, observational studies could use thousands or
millions of subjects if there were enough observers. However because observational studies
are generally conducted in depth, with data that are often subjective and difficult to quantify
the data by two or more observers may not be readily comparable.
3. Compared to interviewers observation might be less expensive in terms of money and
equipment but it costs more man – hours spent in the field and often personal sacrifices to
adapt to the conditions of the field and the research must be conducted by a trained and
competent researcher.
4. Observation cannot be used to study attitudes and opinions. Attitudes can de defined as
readiness or predisposition to behave or react in a certain way towards persons, objects and
institutions. The readiness or predisposition cannot be readily investigated with observation

25
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
5. Our sense organs are inadequate what we observe or perceive are determined by the prevailing
and current physiological status of the body, for example a hungry man is more likely to notice
signs of food than a man who is not hungry.
6. Behavior which is frequent and periodic extends over a long time and behavior of small groups
may not be studied with observation unless the researcher is willing to spend time with the
group and the observed are willing to accommodate him or her in their set up.

4. Focus group discussion

Characteristics and uses of focus group discussions

A FOCUS GROUP DISCUSSION (FGD) is a group discussion of approximately 6 - 12 persons
guided by a facilitator, during which group members talk freely and spontaneously about a certain
topic.
A FGD is a qualitative method. Its purpose is to obtain in-depth information on concepts, perceptions
and ideas of a group. A FGD aims to be more than a question-answer interaction. The idea is that
group members discuss the topic among themselves, with guidance from the facilitator.
Strengths and limitations
Implementation of FGDs is an iterative process; each focus group discussion builds on the previous
one, with a slightly elaborated or better-focused set of themes for discussion. Provided the groups
have been well chosen, in terms of composition and number, FGDs can be a powerful research tool
which provides valuable spontaneous information in a short period of time and at relatively low cost.
FGD should not be used for quantitative purposes, such as the testing of hypotheses or the
generalization of findings for larger areas, which would require more elaborate surveys. However,
FGDs can profitably complement such surveys or other, qualitative techniques. Depending on the
topic, it may be risky to use FGDs as a single tool. In group discussions, people tend to centre their
opinions on the most common ones, on ‗social norms. In reality, opinions and behaviour may be
more diverse. Therefore, it is advisable to combine FGDs with at least some key informant and in-
depth interviews. Explicitly soliciting other views during FGDs should be routine as well.
In case of very sensitive topics, such as sexual behaviour or coping with HIV/AIDS, FGDs may also
have their limitations, as group members may hesitate to air their feelings and experiences freely.
One possible remedy is the selection of participants who do not know each other (e.g., selection of
children from different schools in FGDs about adolescent sexual behaviour), while assuring absolute
confidentiality.
It may also help to alternate the FGD with other methods, for example, to precede it by a self-
developed role play on sexual behaviour, or to administer a written questionnaire immediately after

26
 Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
the FGD with open questions on sexual behaviour in which the participants can anonymously state
all their questions and problems.

Another way to ensure confidentiality in a FGD on a sensitive topic is giving participants an option
to introduce themselves under any name they would like to use (not necessarily their own). Further,
before the discussion, it should be stressed that they may bring up experiences of friends and
brothers/sisters as well as their own, and that it is not necessary to bring painful personal experiences
in the open.

II. How to conduct a focus group discussion

Points to be considered when preparing the FGD Recruitment
of participants:
• Participants should be roughly of the same socio-economic group or have a similar
background in relation to the issue under investigation. The age and sexual composition of the
group should facilitate free discussion.
Often you therefore need to obtain information on a topic from several different categories of
informants who are likely to discuss it from different perspectives in separate FGDs, though
in a later stage groups may be joined (see examples 3,4 and 5).
Always ensure confidentiality of opinions: Ask co-operation from the group members as
well, to keep what has been discussed confidential. If group members present very personal
problems and need advice or help, this should be followed up after the FGD.
Participants should be invited at least a day or two in advance, and the general purpose and
procedures of the FGD should be explained, in order to obtain their consent to join.
• Selection of participants:
If you are an outsider in the research area, you may have to rely on your key informants for
the first selection of participants in FGDs. Your key informants to whom you have explained
thoroughly the purpose and the process of the FGD might each suggest some individuals who
could be invited to a focus group discussion.
Note that the key informants may select persons similar to themselves so that you do not get
an adequate variety of views in your discussion group. So in your explanations be sure to
emphasize that you want a group of people that can express a range of views, to be able to
have a proper discussion. Participants in a first FGD may assist to find relevant participants
for other groups.

27
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
Another way of getting participants is to conveniently select individuals in a systematic way,
to try and ensure a range of views. You might, for example, ask every third or fourth person
you find. This method might be more suitable in urban areas.
• Physical arrangements:
Communication and interaction during the FGD should be encouraged in every way possible.
Arrange the chairs in a circle. Make sure that there will be no disturbances, sufficient
quietness, adequate lighting, etc. Try to hold the FGD in a neutral setting which encourages
participants to freely express their views. A health centre, for example, is not a good place to
discuss traditional medical beliefs or preferences for other types of treatment.
• Preparation of a discussion guide:
There should be a written list of topics to be covered. It can be formulated as a series of open-
ended questions. Guides for different groups gathered to discuss the same subject may vary
slightly, depending on their knowledge or attitudes and how the subject should first be
explored with them.
Conducting the session
One of the members of the research team should act as ‗facilitator or ‗moderator for the focus group
discussion. One should serve as ‗recorder. The facilitator should preferably be as close as possible to
the participants in their characteristics (same sex, roughly same age, etc.).
Functions of the facilitator
The facilitator should NOT act as an expert on the topic. His or her role is to stimulate and support
discussion.
Introduce the session
Introduce yourself as facilitator and introduce the recorder. Let participants introduce
themselves with whatever names they wish to use. Put the participants at ease and explain the
purpose of the FGD, the kind of information needed, and how the information will be used
(for the planning of a health programme, an education programme, etc). Ask permission to
use a tape-recorder, let people hear their own voices before the session starts. You might offer
drinks and allow some informal discussion before the actual session starts.
Encourage discussion
Be enthusiastic, lively, and humorous and show your interest in the groups’ ideas. Formulate
questions and encourage as many participants as possible to express their views. Remember
there are no ‗right or ‗wrong answers. React neutrally to both verbal and non-verbal
responses.

28
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
Encourage involvement
Avoid a question-and-answer session. Some useful techniques include:
— Asking for clarification:
‗Can you tell me more about. . . ?
— Reorienting the discussion when it goes ‗off the track:
Saying: ‗Wait, how does this relate to. . . ?
Saying: ‗Interesting point, but how about. . . ?
Using one participant‘s remark to direct a question to another, for example, ‗Mrs. X said
. . . , but how about you, Mrs. Y?
— When dealing with a dominant participant, avoiding eye contact or turning slightly away
to discourage the person from speaking, or thanking the person and changing the subject.
— When dealing with a reluctant participant, using the person’s name, requesting his/her
opinion, making more frequent eye contact to encourage his/her participation.
Deal correctly with sensitive issues. If you notice that the discussion stops when dealing with
a sensitive topic, you could ask participants (if literate) to anonymously write down their
responses or opinions on the topic. Alternatively, you could summarise for the group some of
the opinions from previous focus group discussions, focusing on one or two major contrasting
opinions. Still another strategy is to form sub-groups, and to get a member of the sub-group
to summarise and present the opinions of their sub-group members after which the whole
group can still discuss these opinions.
Build rapport, empathise
Observe non-verbal communication. Ask yourself, ‗What are they saying? What does it mean
to them? Be aware of your own tone of voice, facial expressions, body language, and those
of the participants.
Avoid being placed in the role of expert
When asked for your ideas or views by a respondent, remember that you are not there to
educate or inform. Direct the questions back to the group by saying: ‗What do you think,
‗What would you do? Set aside time, if necessary, after the session to give participants the
information they have asked for.
Do not try to comment on everything that is being said. Don‘t feel you have to say something
during every pause in the discussion. Wait a little and see what happens.
Control the rhythm of the meeting, but in an unobtrusive way
Listen carefully, and move the discussion from topic to topic. Subtly control the time allocated
to various topics so as to maintain interest. If participants spontaneously jump from one topic
29
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
to another, let the discussion continue for a while since useful additional information may
surface; then summarise the points brought up and reorient the discussion.
Take time at the end of the meeting to summarise, check for agreement and thank the
participants
Summarise the main issues brought up, check whether all agree and ask for additional
comments. Thank the participants and let them know that their ideas have been a valuable
contribution and will be used for planning the proposed research, intervention, or health
education materials.
Listen for additional comments and spontaneous discussions which occur after the meeting
has been closed.
Functions of the recorder
The recorder should keep a record of the content of the discussion as well as emotional reactions and
important aspects of group interaction. Assessment of the emotional tone of the meeting and the group
process will enable you to judge the validity of the information collected during the FGD.
Items to be recorded include:
• Date, time, place
• Names and characteristics of participants
• General description of the group dynamics (level of participation, presence of a dominant
participant, level of interest)
• Opinions of participants, recorded as much as possible in their own words, especially for key
statements
• Emotional aspects (e.g., reluctance, strong feelings attached to certain opinions)
• Vocabulary used - particularly in FGDs that are intended to assist in developing
questionnaires or health education materials
• Spontaneous relevant discussions during breaks or after the meeting has been closed
It is highly recommended that a tape-recorder be used to assist in capturing information. Even if a
tape-recorder is used, notes should be taken as well, in case the machine malfunctions and so that
information will be available immediately after the session for discussion.
If there is no reliable tape-recorder available, it is advisable to have two recorders.
A supplementary role for the recorder could be to assist the facilitator (if necessary) by drawing his
or her attention to:
• missed comments from participants
• missed topics (the recorder should have a copy of the discussion guide during the FGD) If
necessary, the recorder could also help resolve conflict situations within the group that the
facilitator finds difficult to handle on her own.
30
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©

Number and duration of sessions

Number of sessions
The number of focus group sessions to be conducted depends upon project needs, resources,
and whether new information is still coming from the sessions, (that is, whether contrasting
views within and between various groups in the community are still emerging). If not, you
may stop.
One should plan to conduct at least two FGDs for each sub-group (for example, two for males
and two for females). Otherwise you have no way of assessing whether the information you
get from the first FGD is representative for that group.
Duration
A focus group session typically lasts up to an hour and a half. Generally the first session with
a particular type of group is longer than the following ones because all of the information is
new. Thereafter, if it becomes clear that all the groups have a similar opinion on particular
topics, the facilitator may be able to move the discussion along more quickly to other topics
which still elicit new points of view.
Conducting an FGD
Participants working in groups of 6-12 conduct an FGD among themselves. First
let each group select a facilitator and a reporter
• Preparation of discussion guides
• Discussion
NB: It may be instructive to let the facilitator and reporter prepare the discussion guide for their
group together with members of another group. Then the facilitator and reporter could come back
to their own group with the guide when the FGD is to start. This resembles the real situation,
where FGD members do not know which questions will be asked.

Ethics in social research

Ways of ensuring the rights and welfare of persons that are subjects are upheld.

2 Ethical considerations in social research

1. Informed consent
A researcher must ensure the respondents have all the information regarding the study before
starting. This is obtained via signing what’s known as a consent form/letter which certifies that the

31
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
respondent has read and clearly understood the terms of the study and is willing to participate out
of free will.

Reasons for informed consent

• Freedom is a natural right

• Sign of respect
• Safeguard against hazardous research procedures
• Reduces researcher's legal liability

Elements of informed consent

• Competence. With competence, the researcher should ensure that the study involves
participants that are of sound mind and their will cannot be questioned or doubted in other words,
people below the age of 18 are considered incompetent, those with unsound mind, children.
However, for those deemed incompetent to be part of any study, consent is to be obtained from
their guardians accepting the proceedings of the study.

• Voluntarism. Participation in any study is out of one’s free will .i.e. a person has to fully
agree without compulsion to participate or coarsed into participation.

• Full information. Participants must be availed with full information concerning the study,
e.g. information concerning their roles, the need for the study among other reasons.

• Comprehension. The researcher must ensure optimal understanding from the respondents
before proceeding with the study. This can be attained via asking questions or requesting for
feedback from them.

2. Privacy
Elements are namely;
a) Sensitivity of information. The higher the sensitivity the more privacy required and vice
versa.
Information about one’s health is deemed sensitive therefore, in such cases, the researcher
should ensure that confidentiality is sworn and promised to the respondent in order to
create a common ground.

b) Settings being observed. Settings being observed determine the element of privacy for
example, in an office or home setting, the privacy of the respondent should be respected and
consent has to be obtained before the researcher convenes.

32
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
c) Dissemination of information. This is the way the information captured is to be distributed
and what the researcher must keep in mind when doing so. This can be ascertained in the
following ways;

(i) Anonymity. When it gets to distribution of information, names of the respondents must
be kept away and other identifiers for issues of anonymity.

(ii) Confidentiality. Confidentiality must be ensured by ensuring that the information

provided is purely for academic purposes and they shall not fall in any wrong hands.

Proposal/report writing

SCHOOL STUDENTS: A CASE STUDY OF MAKERERE COLLEGE SECONDARY

SCHOOL KAMPALA.

BY

NAME

DECEMBER, 2021

INTEREST ENGAGEMENT AND ACADEMIC ACHIEVEMENT AMONG SECONDARY

SCHOOL STUDENTS: A CASE STUDY OF MAKERERE COLLEGE SECONDARY
SCHOOL KAMPALA.
33
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©

BY

NAME

REGISTRATION NUMBER

A RESEARCH PROPOSAL SUBMTTED IN PARTIAL FULFILLMENT FOR THE AWARD

OF A DIPLOMA IN PUBLIC HEALTH OF MAKERERE BUSINESS TRAINING CENTRE
KAMPALA

DECEMBER, 2022

34
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
DECLARATION

I …………………………… declare that this research proposal is my original work and has never
been submitted to nay institution or school for a similar or any other degree or diploma.
……………………………… …………………………….
Signature Date

APPROVAL
This research proposal titled ………………………………………………………has been written
under the supervision of;
………………………………

…………………………….
Name Date

………………………………
Signature

DEDICATION

This research proposal is dedicated to all the students of research class year 2018.

ACKNOWLEDGEMENT

Would like to extend my utmost gratitude unto the contribution of my friends who helped in the
completion of this research proposal.
ABSTRACT
(comes last after proposal writing)
Summary of the proposal, not more than 120 words

TABLE OF FIGURES

(For any drawings, tables, charts or graphs make a list under this section)

TABLE OF ACRONYMS/ABBREVIATIONS
(For any abbreviations within your content, make a listing under this section; giving their
meaning)

35
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
TABLE OF CONTENTS

DECLARATION ............................................................................................................................ 2
APPROVAL ................................................................................................................................... 2
DEDICATION ................................................................................................................................ 2
ACKNOWLEDGEMENT .............................................................................................................. 2
ABSTRACT .................................................................................................................................... 2
TABLE OF FIGURES .................................................................................................................... 3
TABLE OF ACRONYMS/ABBREVIATIONS............................................................................. 3
TABLE OF CONTENTS ................................................................................................................ 3
CHAPTER ONE ............................................................................................................................. 4
1.0 Introduction......................................................................... Error! Bookmark not defined.
1.1 Background of the study....................................................................................................... 4
1.2 Problem statement ............................................................................................................... 4
1.3 General objective of the study.............................................................................................. 5
1.4 Specific objectives of the study ............................................................................................ 5
1.5 Research questions............................................................................................................... 5
1.6 Scope of the study................................................................................................................. 5
1.7 Significance of the study ...................................................................................................... 6
1.8 Limitations of the study ........................................................................................................ 6
CHAPTER TWO: LITERATURE REVIEW ................................................................................. 6
2.0 Introduction.......................................................................................................................... 6
2.4 Conclusion .......................................................................... Error! Bookmark not defined.
2.5 Research question /hypothesis ............................................ Error! Bookmark not defined.
CHAPTER THREE: METHODOLOGY ....................................................................................... 7
3.0 Introduction.......................................................................................................................... 7
3.1 Research design ................................................................................................................... 7
3.2 Population ............................................................................................................................ 7
3.3 Sample .................................................................................................................................. 7
3.4 Instruments
........................................................................................................................... 7 3.5
Measures
.............................................................................................................................. 7
3.6 Procedure ............................................................................................................................. 7

36
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
3.7 Quality control ..................................................................................................................... 7
3.8 Data management ................................................................................................................ 8
3.9 Data analysis ....................................................................................................................... 8
References ......................................................................................................................................
8 Attachments
.................................................................................................................................... 8
1. Budget ...................................................................................................................................... 8
2. Time schedule .......................................................................................................................... 8

CHAPTER ONE: INRODUCTION

Introduce to the reader what will be in this chapter
1.0 Background of the study (1 and half page)
Para 1. Focusing on the dependent variable of the study in other words the outcome variable.
History about it but at this point do not define the variable, using literature of other authors and
availing citations e.g. According to Askon (2021)
Para 2. Bring out the impact of the variable (DV) on the context under study. In other words state
the factors or variables that affect the dependent variable and the would be out comes (Askon,
2021).
Para 3. when explaining your variable ensure that you link it to the dependent variable.
Para 4. Engagement will be related with Academic achievement.
Para 5. Landing paragraph were by the researcher all the variables (3), you show their relationship
1.2 Problem statement
(HALF A PAGE)

• Ist para. Appreciate what has been done in Uganda.

• 2nd para. Talk about what is improper (DV) In other words how is it a problem and why?
• 3rd para. The bad implications of what's wrong or not proper (if nothing is done what will
be the bad outcome.

1.3 General objective of the study

It's derived from the topic it should bare all three variables and stated in its fullness E.g. To find out
the relationship between students’ engagement, sleeping before an exam and performance among
high school students of Bundibugyo H/S.

37
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
1.4 Specific objectives of the study
These should be subsets of the general objective. They should be statements connecting
two variables that are derived from the purpose. The objectives normally unpack the
purpose. Starting with
To find out or To determine To assess the relationship between Covid 19 and convenience
among patients of such and such a location.
To determine the relationship between convenience and Hiv patients

•
1.5 Research questions
Research questions are derived from the specific objectives of the study.

• What is the relationship between convenience and Hiv patients?

1.6 Scope of the study
• Geographical scope: Indicates the location, place or district where the study is going to take
place: And why that location

• Conceptual scope: Indicate the details of variables of interest. Define the variables according
to authors.
• Time scope: How long will the study take to be conducted. You may indicate that, the study
will be conducted for a period of two weeks.
• Sample scope: Mention the sample size that will be required for your study. This is obtained
from the place where the study is to be conducted.
1.7 Significance of the study
It should answer the question "so what". Indicate how your research can be used to solve The
problem at hand. It's a speculative statement. (Use may)
1.8 Conceptual framework

Interest Engagement Academic performance

You need to explain the above arrows by indicating the following (in a paragraph format)

Interest directly influences engagement, engagement significantly affects academic performance

and interest has a direct relationship with academic performance.

38
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
CHAPTER TWO: LITERATURE REVIEW
Summarizes what's covered in the literature review (one small paragraph)
This should highlight what other people have done/indicated on previous research subsections
2.0 Interest (Describe the historical background of this variable according to different scholars)
2.1 Engagement (Describe the historical background of this variable according to different
scholars)
2.2 Academic interest (Describe the historical background of this variable according to different
scholars)
2.3 Interest and engagement 2 pages

2.4 Engagement and academic performance 2 pages

2.5 Interest and academic performance 2 pages

CHAPTER THREE: METHODS SECTION

A summary of what's in the methodology section
3.1 Research design
Indicating the design as well as the reason for choosing it
3.2 Population

All possible members of the study

3.3 Sample
Specify the following;

• Nature of the sample

• Number
• Selection methods
3.4 Instruments
State what instrument you will use (in one statement)
3.5 Measures

List the variables that are going to be in the instrument, under different sections.

• Section A: Background information items

• Section B: Interest
• Section C: Engagement
• Section D: Academic achievement

3.6 Procedure

39
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
Provide details, from questionnaire construction let's say, up to when data is ready for
analysis.

3.7 Quality control

Indicate how you will ensure validity and reliability.

3.8 Data management

Indicate how you will code your data

3.9 Data analysis

Indicate how you will test your hypotheses
REFERENCES
Indicate all cited people/sources in the reference list (APA format of writing)
Attachments
1. Budget
Give items that you will need to pay for. Put this information in a table form with different columns.

2. Time schedule
Give time lines according to different activities e.g. August 2021-May 2022
3. A draft instrument like a questionnaire

Note! Font (Times New Roman), color should be (black /automatic), font size (12), line and paragraph
spacing (2.0)

40
Research methods and project (2022) Contact: [email protected]/ 0783141929 or
0706513135
Makerere Business Training centre ©
TABLE FOR DETERMINING NEEDED SIZE s OF A RANDOMLY CHOSEN SAMPLE FROM
A GIVEN FINITE POPULATION OF N CASES SUCH THAT THE SAMPLE PROPORTION p
WILL BE WITHIN ± .05 OF THE POPULATION PROPORTION p WITH A 95 PERCENT
LEVEL OF CONFIDENCE
Population Sample Population Sample Population Sample
Size Size Size Size Size Size
10 10 220 140 1200 291
15 14 230 144 1300 297
20 19 240 148 1400 302
25 24 250 152 1500 306
30 28 260 155 1600 310
35 32 270 159 1700 313
40 36 280 162 1800 317
45 40 290 165 1900 320
50 44 300 169 2000 322
55 48 320 175 2200 327
60 52 340 181 2400 331
65 56 360 186 2600 335
70 59 380 191 2800 338
75 63 400 196 3000 341
80 66 420 201 3500 346
85 70 440 205 4000 351
90 73 460 210 4500 354
95 76 480 214 5000 357
100 80 500 217 6000 361
110 86 550 226 7000 364
120 92 600 234 8000 367
130 97 650 242 9000 368
140 103 700 248 10000 370
150 108 750 254 15000 375
160 113 800 260 20000 377
170 118 850 265 30000 379
180 123 900 269 40000 380
190 127 950 274 50000 381
200 132 1000 278 75000 382
210 136 1100 285 10000 384

THANKS FOR YOUR ATTENDANCE AND MOST ESPECIALLY YOUR’E

COOPERATION
BEST OF LUCK

41