Research Methodology

2014
HCOB 2403:RESEARCH METHODS
MOSESOCHIENG GWEYI
THE CO-OPERATIVE
UNIVERSITY COLLEGE
OF KENYA
ANTE RESEARCH METHODS
Contact Hours Lectures Seminar/Practical Totals
Credits Credits Exam Hours
Course Rationale:
Description
Research may be defined as a disciplined inquiry or systematic investigation
aimed at providing solutions to problems.
The main purpose of research is to advance or discover new knowledge and
improve practice through scientific process. To ensure quality and timely
completion of a research project, clear guidelines and procedures are
necessary.
The purpose of this module is to help the student acquire knowledge and
skills of research methods and their applications to the solutions in both
academics research and in management decision- making process.
General This course is intended to help the student to be able to prepare a research
Objective proposal, conduct and submit a comprehensive research project report on a
topic in microfinance using knowledge gained in the course.
 Demonstrate knowledge on the process of conducting research and

Specific By the end of this course, students will be able to:
Objectives
how to use findings to inform managerial decision making
 Identify the problem definition and understand the research process
 Have basic understanding of data collection and data analysis.
 Interpret research findings to inform managerial decision making.
 Identify a research problem in a business field and write a research
proposal and research project
Course Content 1: Introduction to Research
 Selecting A Research Topic

2: The Research Process (Steps in the research process)
 Formulating The Research Problem

 Defining Concepts And Developing Conceptual Framework
 Literature Review
 Selecting The Research Design
 Selecting The Data Collection Method
 Selecting The Survey Method
 Preparing Data Collection Instruments
 Selecting Data Analysis Tools
 Report Writing And Dissemination Of Results
Research Methods Page 2

3: Chapter One: Introduction
4: Chapter Two: Literature Review
5: Chapter Three: Research Methodology
6: Chapter Four: Data Analysis and Presentation of Results
7: Chapter Five: Summary, Conclusions and Recommendations
8:Miscellenous
 Introduction to research
Key Learning  The research process

Points
Preparing the research proposal
 Preparing the final research project report
Training  Short Lectures
Methods  Small group discussions followed by presentations and panel
discussions
 Individual and group home works /assignments.
Student Activity The major part of this section is to be covered as an independent study. The
contact time will be used for consultations between students and supervisors.
Each student will be required to produce a system and related
documentation, and participate in oral presentation and defense of the
research proposal.
Recommended Author (and year of Title Publisher and place of
Reading publication) publication
O.M Mugenda and A.G Research Methods : Acts Press

Mugenda(2003) Quantitative and Qualitative
approaches
M. Saunders, P. Lewis and Research Methods for Dorling Kindersley Pvt.

A. Thornhill (2005) business students 3rd Edition Ltd
Kate L. Turabian A Manual for Writers of The University of

Term Papers, Theses, and Chicago Press
Dissertations (Chicago
Guides to Writing, Editing,
and Publishing)
Orodho, J.A(2000) Techniques of Writing Masola Publishers,
Research Proposals and Nairobi
Reports in Education and
Social Sciences

Other Support Borg, R.W. and M.D. Gall. 1989. Educational Research: An Introduction.
Materials and New York: Longman, Inc.
Resources Chandran, Emil. 2004. Research Methods: A Quantitative Approach.
Nairobi: Daystar University.
Dornan, Edward A. and Charles W. Dawe. 1984. The Brief English Module.
Little: Brown and Company.
Higham, Nicholas J.1993. Module of Writing for the Mathematical Sciences,
SIAM Press.
Orodho, J.A. 2004. Techniques of Writing Research Proposals and Reports
in Education and Social Sciences. Nairobi: Masola Publishers.
Peil, Margaret. 1995. Social Science Research Methods: A Module for
Africa. Nairobi: EAEP.
Strunk, William Jr. and E. B. White. 1972. The Elements of Style. New York:
Macmillan

RESEARCH METHODS
COURSE OUTLINE
ASSESSMENT:
A. COURSEWORK AND PROJECT PROPOSAL
(1) Assignments and/or CAT……………… 20%
(2) Research Proposal a) Proposal document 30%
b) Presentation & defense 20%.
50%
(3)Final Exam ………………………………………… 30%
TOTAL 100%
B. FIELDWORK AND FINAL PROJECT
(1)Fieldwork and Final Research Project Report..………………………100%

LESSON ONE: INTRODUCTION TO RESEARCH
1.1 What is research?
 There are many ways of defining “research”
 To research is to carry out a diligent inquiry or a critical examination of a given
phenomena.
 Research also involves a critical analysis of existing conclusions or theories with regard
to newly discovered facts
 Research is a systematic, controlled, empirical, and critical investigation of hypothetical
prepositions about the presumed relations among natural phenomena
 Research is the process of arriving at dependable solutions through a systematic
collection, analysis and interpretation of data
 Research is the careful and systematic inquiry into or examination of a field of
knowledge in order to establish facts and principles.
All definitions emphasize that research is a process, not an event. It must therefore be
carefully planned, implemented, disseminated, and consumed.
1.1 Purposes of research
 The main purpose of research is to discover new knowledge. This involves the
discovery of new facts, their correct interpretation and practical application.
 Secondly, is to describe a phenomenon. Accurate identification of any event involves
thorough description.
 Thirdly, is to enable prediction. This is the ability to estimate phenomenon. We
sometimes use a set of variables to predict a given variable.
 The fourth purpose of research is to enable control. In scientific research control is
concerned with the ability to regulate the phenomenon under study. Many scientific
experiments are designed to achieve this objective.

 The fifth purpose of research is to enable explanation of phenomenon. Explanation
involves accurate observation and measurement of a given phenomenon.
 The sixth purpose of research is to enable theory development. Theory development
involves formulating concepts, laws and generalization about a given phenomenon
1.3 Distinguishing characteristics of research
 Research is systematic
 Research is controlled
 Research is empirical. It deals with data, which is tested scientifically.
 Research is self-correcting. The results of research are open to public scrutiny.
1.4 Research and Knowledge
Suppose you want to know why many clients use loans outside the business. There are four
sources of knowledge, namely: -
 Experience
 Reasoning
 Authority
 Research
Research is the most important tool for advancing knowledge. It is also the most important tool
for promoting progress, relating to our own environment, enhancing the accomplished of our
purposes and for resolving conflicts within any sector such as microfinance.
Social research studies the problems of man in a social set up. Being a very human process, it is
prone to error and bias. To minimize the influence of error and bias on their findings, researchers
have developed various procedures. As such the approach to inquiry in microfinance that
involves the conduct of research is different from other approaches to learning about
microfinance and improving it.
For that reason, a research ranks higher above other approaches like; -

 Folklore and mysticism (including magic)
 Dogma and tradition
 Casual observation
1.5 Areas of research in microfinance
 Opinions and attitudes
 Needs of the people
 Feasibility of proposed microfinance products and/or activities
 Identifying relevant approaches and models
 Evaluation of ongoing programs, current products, policies, procedures, approaches, etc.
 How certain events occur and the relationship between events. This has got to do with
human behavior and how certain events affect human behavior.
1.6 Quality Requirements of Research Projects
Whether a student is seeking to complete a diploma, degree at an undergraduate level or
Master’s level, one key factor that must be borne in mind is quality. Quality is generally defined
as conformance to requirements or fitness for purpose. Degree/Diploma project demonstrates the
student’s readiness to join scholars and practitioners in advancing the knowledge and practice in
the real world of business. Consequently, students are expected to produce quality research
projects that:
 Make contribution to the knowledge in the discipline,
 Address current problems of interest to the practitioners,
 Demonstrate a mastery of a specialization area within the degree/diploma program,
 Reflect the integration of practice and scholarship, and
 Are of publishable quality.
1.7 Research Project Prerequisite

The major prerequisite for the research project is Business Statistics and Research Methods. All
students are required to complete Business Statistics and Research Methods before registering
for the research project course. Each student taking Business research methods must develop a
detailed research proposal for the intended research project .The research proposal should focus
on the student’s area of concentration within their diploma program, in this case, Microfinance.
1.8 Role of the Supervisor in Research Project
The supervisor should be an expert or experienced in the intended area of study. The major role
of the project supervisor is to supervise the design and development of the research proposal, the
conduct of the research, and the preparation of the final research project document.
The supervisor should ensure that the research project is academically sound, is clearly and
correctly written, and provides an original contribution to the field.
1.9 The Research Proposal
The research proposal is a blue print or a plan for an intended study. Research proposal
preparation is essential in the development and pursuit of a research endeavor. The quality of the
final research project often depends on the quality of the research proposal. Consequently, each
student must develop a comprehensive research proposal before registering for the research
project
The research proposal for the project should consist of three major chapters or sections including
introduction, literature review and methodology. In addition to the three major chapters, the
research proposal should also provide an abstract, reference or bibliography, implementation
schedule and, implementation budget. The three major chapters or sections (introduction,
literature review, and methodology) of the research proposal should correspond to the first three
sections of the research project report in terms quality and comprehensiveness. The only
difference being that, the introduction and methodology sections are written in present or future
tense in the research proposal and past tense in the research project report.

1.9.1 Introduction
The introduction section of the proposal should include:
• Background of the problem
• Statement of the problem
• Purpose of the study or general objective
• Research questions or specific objectives or hypothesis. The hypothesis should be stated if the
study involves experimental designs or statistical tests.
• Importance or justification or significance of the study
• Scope of the study
• Chapter Summary
1.9.2 Literature Review
The literature review section of the proposal should present a review of the literature related to
the problem and purpose. The literature review section should therefore be organized or
categorized according to the research questions or specific objectives in order to ensure
relevance to the research problem. It should be written using appropriate writing style such as the
American Psychological Association (APA) style.
1.9.3 Research Methodology
The research methodology section of the proposal should provide explanation and description of
the methods and procedures used in conducting the study. This section should include:
• Introduction
• Research design
• Population and sample
• Data collections methods (instrumentation)
• Research procedures
• Data analysis methods

• Chapter Summary
1.10 Submission of the Final Research Project
The supervisor must approve the final document before submission. The supervisor should
ensure that the final document is of high quality and complies with the appropriate writing style
such as the American Psychological Association (APA) style.
1.11 Research Project Format
Research project reports consist of two main sections, the preliminary section or front matter and
the text or body.
1.11.1 The Sequence of Front Matter
The front matter or preliminary pages in a research project should be presented in the following
sequence:
i. First title page
ii. Second title page
iii. Student’s declaration
iv. Copy right page
v. Abstract
vi. Acknowledgement (optional)
vii. Dedication (optional)
viii. Table of content
ix. List of tables (if more than four tables are in the text)
x. List of figures (if more than four figures are in the text)
xi. Definition of terms
1.11.2 Front Matter Pagination

The front matter or preliminary pages of a research project should be paginated appropriately
with small Roman numbers at the bottom center of the page. The pagination should be as
follows:
i. Second title page is counted as i, but not paginated
ii. Student’s declaration is paginated as ii
iii. Copyright page is paginated as iii
iv. Abstract is paginated as iv - v
v. Acknowledgement is paginated depending on the abstract
vi. Dedication is paginated depending on the acknowledgement
vii. Table of content is paginated depending on the dedication
viii. List of tables is paginated depending on the table of content
ix. List of figures is paginated depending on the list of tables
1.11.3 The Abstract
The abstract is required with all research projects. The purpose of the abstract is to provide a
clear and concise summary of the:
• Purpose or problem
• Methodology used
• Major findings and conclusions
• Major recommendations or suggestions for improvement
The abstract should be approximately 300 - 400 words. It should be prepared after the five
chapters or major sections of the project report have been written but presented as front matter
material in terms of sequence
1.11.4 The Body or Text
The majority of research projects in business, economics and social sciences follow a five-model
chapter. The major sections in the five-model chapter include:

• Chapter 1: Introduction
• Chapter 2: Literature Review
• Chapter 3: Methodology
• Chapter 4: Data Findings and Presentation of Results
• Chapter 5: Summary, Conclusions and Recommendations.
In addition to the five major sections, a research project should include an abstract, reference or
bibliography, and appendix for data collection instruments and other relevant materials used in
the study.
1.12 REVIEW ASSIGNMENTS
1. State the meaning of research and purposes of research?

2. What are the Distinguishing characteristics of research?
3. What are the most probable areas of research in microfinance?

LESSON TWO:
THE RESEARCH PROCESS
Steps in the Research Process

Scientific research is a systematic inquiry. It must therefore be carefully planned and conducted.
This entails going through a clear step-by-step process. This process consists of ten steps as
outlined in the diagram below
1. Selecting a research topic
2. Formulating the research problem
3. Defining concepts and developing

conceptual framework
4. Literature Review
5. Selecting the research design
6. Selecting the data collection

method
7. Selecting the survey method
8. Preparing the data collection

instrument(s)
9. Selecting data analysis tools
10. Report writing

Step 1: Selecting a Research Topic
It is important to choose a topic, which can be studied within various constraints facing the
researcher. These include, time, finances, and ability of the researcher.
Whereas topics for research may be selected for the researcher e.g. by those in authority, it is
better for one to come up with his/her own topic. Academic research is usually left to the
individual scholars, whether students or members of staff. Each then chooses a topic from an
area that s/he is interested in and comfortable with. The process is as follows:
1. Identify the Broad Area

The criteria for choosing a research area comprises of the following three considerations.
(i) Need - ask yourself whether there is need for a study in the area. Who needs it and why? The
selection of a topic is governed by the need to address some problems or questions or understand
some given situations.
(iii) Interest or concern - What is the interest of the concerned college department, industry,
sector or institution? For instance the micro-finance sector may be interested in determining the
causes of the low level of reach by MFIs to enterprises that need financial services.
(iii) Feasibility - The research chosen must be feasible. Is it possible and practical to achieve the
research easily and conveniently? The scope, time, financial and other resources available affect
the feasibility of a research.
2. Word the Topic

Once the researcher is satisfied with the broad area of study, he words the topic appropriately.
The topic is stated in words that indicate the focus, problem. or issue of the research. Chandran
suggests the following guidelines for wording of the research topic:


The topic should capture fully the focus or the issue of the research.
It should have clear reference to the specific population or group of people or the objects
 It should include the key or main variables of the research

targeted for the research
 It should reveal the nature of the research (i.e. whether qualitative or quantitative)
 It may include references to the time period of the issue or the research (e.g. in the case of
 It does not necessarily have to be a statement - it could be a phrase or a question

historical research the date of the case study is optional in a topic that is current)
 The wording has to be precise.

Examples:
- Attitude of small-scale furniture makers in Nakuru towards management consultancy
services.
- Factors affecting growth of transport businesses owned by women in urban centers in
central province.
3. Build Preliminary Knowledge

The purpose of looking for preliminary knowledge is to enable the researcher to ascertain
whether or not there is really a research problem in the area (topic chosen). It also helps the
researcher to find out what is already known about the topic. Overall, it saves the researcher time
and other resources, which would otherwise be used in pursuing a research that he/she is forced
to discard midstream. Some of the resource of the preliminary information is: -

- Studies that have already been conducted
- Recommendations made by previous studies (especially on areas requiring further research)
- Journals
- Dissertations
- Reports and conference materials
Since research should contribute to knowledge, you should read any material critically. Are there
any flaws in what is already known? Is the research done properly or badly? Could
Conditions have changed over time? Has the research been replicated? Are there obvious gaps in
information? Has the theory been tested adequately?
Step 2: Formulating the Research Problem
The researcher must move on from the topic selection to problem formulation. The concepts or
characteristics that are included in the research frame must be sharpened and the scope narrowed.
By formulating the research problem carefully, the researcher is able to identify the type of data
that needs to be collected. A research problem must be researchable.
Students as well as novice researchers often find it extremely difficult to formulate a research
problem. Sometimes it is a painful and laborious process even for experienced researchers.
 The first step in selecting a research problem is to identify the broad area that one is
Identifying a research problem
interested in. such areas should be related to the professional interests and goals of the
researcher.
 The next step is to identify a specific problem within it that will form the basis of the
research study. This means that the researcher should narrow down from the broad area
 In selecting a specific problem, the researcher should consider the key factors that help in
to a specific problem
 An important research problem is one that should:

identifying a researchable problem.
(i) Challenge some commonly held truism

(ii) Review the inadequacies of existing laws, views and policies
(iii)Lead to findings that have widespread implications in a particular area.
 Existing theories: an existing theory is a good source of research problem

Ways of identifying a research problem
 Existing literature: a systematic reading programme in the generl area of interest is

perhaps the best way of locating specific research problems
 Discussion with experts: Such discussion usually involves experienced and well informed
researchers
 Previous research studies: a review of previous research studies provides the researcher
with researchable project that would when carried out add knowledge
 Replication: this involves carrying outs a research project that has been done previously.
This is done to find out whether findings hold over time and across regions
 The media: issues which are frequently reported in the media can also form the basis of
research problems
 Personal experiences: first hand observations and reflection on intriguing experiences
could be sources of research problems

Stating the problem
A research study usually starts with a brief introductory section. In this section, th researcher
introduces briefly the general area of study. The researcher then narrows down to the specific
problem to be studied. In general, a good problem statement has the following characteristics:
(i) Problem is real. This means that it comes from real life situations rather than the
researcher’s imagination.
(ii) The concepts can be clearly defined. The concepts i.e. characteristics in the problem
are so clear that one can specify in words what the questions are. For example, in the
problem “to determine factors affecting growth of transport businesses owned by
women in urban centers in central Kenya”, the concepts “growth”, “transport’’,
“business”, “urban centers”, and “Central Kenya’’ must should be clearly defined.
- Where concepts are clearly defined, it becomes easier to perceive clearly the
questions in the problem.
(iii) Concepts must be measurable. This could be represented by some evidence, which
can be obtained from direct observation or other activities.
(iv) The research activity is feasible. This refers to the ease and convenience of carrying
out the research.
Problem formulation should be done very cautiously because it affects all subsequent steps in the
research process. It affects the choice of the research design, type of the data, data collection
method and data analysis methods.
 Statement is clear. A clear statement will make it easier for the researches to mentally
A good problem statement has the following characteristics:
conceptualize the problem and put it in research objectives or questions. It should also
show how the concept or variable are related to each other.
 Statement is specific. This is reflected in specific objective or questions. For example

the statement, “Factors affecting growth of businesses owned by women entrepreneurs”
is vague. What type of businesses, where?
 Statement is exhaustive. The statement covers fully all the aspects of a topic including
concepts and relationships. For example, the statement “Factors affecting growth of
businesses owned by women entrepreneurs” is not exhaustive. It does not specify the
type of businesses, the area where they are located and the time period.
Types of Problem Formulation
 Objectives
There are three ways of formulating a research problem.
 Questions
 Hypothesis
(a) Research Objectives
The objective of the research should be stated clearly. They should also be testable, based on
measurable variables of the study. The objectives are important in any research study because:
-They determine the kind of questions to be asked (for gathering data)
-They determine the nature or form of study
-They determine the data collection and analysis procedure to be used.

Research objectives may be of two types - general (broad) and specific. A broad objective
indicates the general focus and direction of the study.
Example – “To find out the annual growth rates of the businesses owned by women in Nairobi”
Specific research study objectives are more specific. They indicate specific aspects like issues,
relationships or associations between concepts and their effect on each other.
Example – “To find out the relationship between age and growth of women owned transport
businesses in Nairobi”
- “To find out the relationship between access to credit and growth of women-
owned transport businesses in Nairobi”
Using a study like “Access and participation in secondary school education among pastoralist
and urban-slum communities in Kenya’’, Orodho1, suggests the following objectives:
 To analyze the enrolment rate of pupils and students in secondary schools in pastoralist
 Find out the current status of the study of the physical facilities and instructional
(Garissa) and urban-slum schools by gender between 1990-2002.
 Analyze the performance of students in KCPE and KCSE by gender in the study districts.
materials in the study districts.
 Uncover the critical non-school based factors causing regional inequalities in students’
access to and participation in primary and secondary school education in Kenya.
(b) Research Questions

The study problem can also be stated as research questions. These are questions that the
researcher would like answered by undertaking the proposed study. (The difference between
research questions and objectives is that research questions are stated in a questions form while
objectives are stated in a statement format). If the questions and objectives are referring to the
same phenomenon, then only one set should be included in the study.
Research questions can also be stated in broad (general) or specific terms. Whereas there are no
 Is the question really important?

set rules of selecting research questions, the following guiding questions can be raised:
 Will the question make a difference?

 Will the question lead to interesting or relevant results?
 Will it lead to policy changes in the organization?
Examples - What is the relationship between age (of business) and growth of women-owned
transport businesses in Nairobi?
- What has been the regional (pastoralist and urban-slum) student enrolment in primary and
secondary school by gender between 1990-2002?
(c) Research Hypotheses
A hypothesis is simply an assumption or some supposition to be proved or disapproved. In
research, it is a formal question that originates from the research problem that the study
anticipates to solve. It is a statement, which is subject to being tested empirically through
scientific investigation resulting in acceptance or rejection.
A hypothesis is also seen as a proposition or set of propositions advanced as an explanation for

the occurrence of particular event. This is an educated guess about possible differences,
relationships or causes of a research problem. A research problem is stated as a hypothesis where
it is possible to test it using scientific methods. Relating an independent variable to some
dependent variable does this. Because the hypothesis (tentative assumption) is made to draw out

and test logical or empirical consequences, the hypothesis should be stated after extensive
literature review.
Research hypotheses should be very specific and limited to the research at hand because they
have to be tested. A hypothesis helps the researcher to delimit the area of research, sharpens his
focus, and indicates the type of data required and the data analysis methods to be used. For each
hypothesis, the researcher should specify the method to be used for analysis.
 They must state clearly and briefly the expected relationship between variables
The characteristics of good hypotheses
 They must be consistent with common sense or generally accepted truths

 They must be related to empirical phenomena
 They must be simple and as concise as the complexity of the concepts involved allows
 They must be testable within a reasonable time
 They must be based on a sound rationale derived from theory or previous research or
professional experience
NB: Not all studies test hypotheses, especially in the case of exploratory and case studies.
Hypotheses may be stated in two forms, directed and null.
Directional/ Alternative hypotheses state the relationship between the variables being studied.
Examples: -
H1 - pre-loan training influences clients’ loan repayment
H2 - There is a positive and significant relationship between the experiences of Credit Officers
and clients loan repayment
Null hypotheses state that no relationship exists between the variables being studied.
Examples:
Ho 1 - Pre-loan training does not influence clients’ loan repayment.
Ho 2 - There is no positive relationship between the experience of credit officers and loan
repayment by their clients.
The null hypothesis is stated so that it can be tested and ultimately accepted or rejected. It is not
necessarily the researcher’s expectations. Nevertheless, it is used because it is better fitted to
scientific techniques, many of which are aimed at measuring the possibility that a difference
found is truly greater than zero. This means that any difference found in the sample is also
present in the population.
Step 3: Defining Concepts and Developing Conceptual Framework
Defining Concepts
A concept is an abstract idea, which can be used to describe situations, events individuals or
groups being studied. It is a term that refers to the characteristics of the situations events,
individuals or groups. Examples of concepts are: role, authority, capital, community, wealth,
poverty, growth, small business, delinquency, default, influence, women-owned, performance,
etc.
A concept may mean different things to different people based on the context and their
experiences. Concepts derive their meaning from a cultural context and are culture or tradition
bound. For example the concept of ‘marriage” has raised interesting debate in the recent past. It

is also important to define concepts for the sake of consistency in measurement. (The data
collection step is simply to measure concepts and represent them in quantities).
NB: (i). A definition of a concept is not the same as an operational definition.

The latter is a description of a concept in terms of measurable indicators, which will be
quantified through empirical data for analysis. An operational definition gives a precise list of
the characteristics to be included so that there can be no doubt of what falls into this category or
does not.
Example
Concept Definition of the Operational Definition
Concept
1) INFLUENCE Power or ability to
Effects: e.g. promptness in repaying
affect someone’s belief
loans, attitude towards loan
or actions repayment
2) SMALL Informal business
- Employing less than 50 people
BUSINESS - Owner-managed
3) WOMEN- Women registered - Registered by a woman
OWNED owner or co-owners - Operated by a woman
- Operational decisions made by the
woman
(ii) It is important to take note of and remember the operational definitions as you read available
literature.
(ii) It is advisable to use the same operational definitions as used in previous works on the topic.
This contributes a great deal to the comparability of results. (It is also easier to assess the flaws
in a definition that has been tried in the field than to know what will happen with a definition,
which has just been created!).
Conceptual Framework
This is a schematic representation of a research problem that includes a network of concepts and
exhibits the flow and direction of their relationships. It is a flow chart that shows which concepts
are related to which others. The course in which the influence between flows is the direction.
Concepts or variables that influence others are called independent variables. Those, which are
influenced by one or more variables, are called dependent variables.
A conceptual framework helps the reader to quickly see the proposed relationships. It is also a
useful step towards an operational definition of concepts. Furthermore, a conceptual framework
enables the researcher to consider the most appropriate steps towards collecting empirical
evidence. Finally a conceptual framework helps the research to separate the effect of the
independent variables from their intervening variables.
An intervening variable is one that comes between the independent and dependent variables,
modifying the effect of independent variables.
Example:
Hypothesis: - “infant death rates will fall as national income rises”
A country may increase its income per capita without lowering the death rate if most of the
income goes to a few families. In this case the distribution of income is an intervening

variable. This is the challenge faced by micro finance researchers e.g. in determining the
impact of financial intervention.
Step 4: Literature Review
Literature review involves the systematic identification, location and analysis of documents
containing information related to the research problem being investigated. Literature review
should be extensive and thorough because it is aimed at obtaining detailed knowledge.
Purpose of Literature Review
For any study to contribute to research knowledge, it should clearly build on the work of others
in the area of inquiry. Literature review is particularly useful to this end as it helps one to
develop a deeper understanding of the problem that he/she intends to investigate.
i. Delimiting the research problem

Selecting a limited problem and investigating it in depth is better than the superficial study of
a broad problem. The literature will also show how other researchers have formulated useful
lines of inquiry within a broad field.
ii. Seeking new lines of inquiry

During the review of literature, one is able to determine what research has already been done
in the area of interest. One should at the same time be on the look out for research
possibilities that might have been overlooked. Identification of new and unexplored areas is
good knowledge in itself.
iii. Avoiding fruitless approaches

Review of literature sometimes identifies several similar studies over a period in the past,
employing approximately the same research methodology and all of which failed to produce
a significant result. If several studies under the same circumstances have been done with the
results confirming the initial findings, it would not be prudent to do yet another similar study.
Such a study would serve no purpose and would only show that the researcher had not done
adequate literature review.
iv. Gaining methodological insights

A good review of literature helps the researcher in identifying possible practical research
methods that he could use. It is therefore necessary to research beyond the results reported.
The methodological insights gained might be useful to other researchers.
v. Identifying recommendations for further research

Every study usually concludes with a discussion of its findings and recommendations for
further research. A researcher should consider these recommendations carefully because
these could provide you with a research problem as well as the justification for studying it.
vi. Seeking support for grounded theory

Many research studies are designed to test a theory that has already been developed.
According to Barney Glaser though, studies can also be designed in a way that data are
collected first, and then a theory is derived from those data 4. This results in a “grounded
theory” i.e. “grounded” in a set of real world data.

When literature review is conducted in this way, it might generate support for the theory. It
might also lead to the researcher(s) to question their own theory or might make them refine
their theory. Ultimately they might even develop ideas for further study. 2
 Be very familiar with the library before beginning the literature review
Steps in Carrying out Literature
 Make a list of key words or phrases to guide your literature

 With the key words and phrases related to the study, one should go to the source of
 Summarize the references on the card for easy organization of literature

literature.
 Once collected, the literature should be analyzed, organized and reported in an orderly
manner
 Make an outline of the main topics or themes in order of presentation.
 Analyse each reference in terms of the outline made and establish where it will be most
 Studies contrary to your topic shouldn’t be ignored such studies should be analyzed and
relevant
 The literature should be organized in such way that the more general is covered first
possible explanation for the difference given.
before the researcher narrows down to that which is more specific to the research
problem.
Major Steps in a Literature Review

Literature review is more likely to be fruitful if one has already developed a preliminary research
problem. The steps in a literature review are highlighted in the framework below. Note that the
steps are not necessary done in the sequence. The results of one step might often lead to a review
of the research problem and any or all the other steps
Step What it entails

1. Search preliminary sources These are indexes to particular bodies of literature.
Examples are journals (that publish articles on small
enterprise or microfinance); books, articles, professional
papers, which are relevant to the research problem.
Look for citations (also called bibliographic citation or

reference) A citation is a description of the document that
identifies its author(s), title, year of publication and
publisher.
NB: Seek assistance from the librarian on this. Make use of

the internet as well
2. Use of secondary sources A document written by someone who did not actually do the
research or develop theories, or express the opinions that
they have synthesized into a literature review.
It helps you to determine whether relevant secondary

sources exist
E.g.- review of literature already done by other researchers

in the area of interest

3. Read primary sources This is a document (e.g. journal article/dissertation) written
by the persons who actually conducted the research, or
formulated the theory or opinions described in the
document.
Obtain and study the original reports of the least, the studies
that are most central to your proposal study.
4. Synthesize the literature To synthesize is to put together, in a coherent manner,
different ideas or theories that have been gathered from
different sources.
In this way the researcher looks for links in the literature

reviewed and relates the current study problem.
The review will have shown that it is already known, not yet
known and the problems or questions that you plan to study.
As you write your literature review (synthesis), show clearly

how the proposed study relates to, and builds upon, the
existing knowledge
Source: Adapted from: Gall, M D, and Borg W R (1996). Educational Research: An

Introduction. New York: Longman. Pp. 114 - 117
When doing literature review, the following research aspects need to be considered:
 Research topic


Research objectives/questions/hypothesis
Research concepts and their relationships to each other


Research design
Research methods – e.g. data collection and data analysis.
Some of the sources of literature available locally are:

 Libraries e.g. KNLS, British Council, Information Library, Macmillan, etc
 Universities and other learning institutions libraries/resource centers e.g. SU, UoN, KU,
JKUAT, Daystar, ANU, CUEA, Kenya Polytechnic, KIBT, EPC, Co-operative College,
 Development institutions/programs e.g. UNDP, WTO Centre, KNCC & I, KNFJKAs, K-

etc.
 Microfinance Institutions – e.g. AMFI, KUSCCO, Individual MFIs, Banks etc.

Rep (KDA/KAS), AFRICAP, Microsave
 Government Ministries/Departments/Agencies e.g. KIBT, Min of Labor, Min of

Planning, CBS, Central Bank, etc.
 Organizations sponsoring you.
Step 5: Selecting the Research Design
Meaning
Chandran sees a research design as, “an arrangement of conditions for collection and analysis of
data in a way that combines their relationship with the purpose of the research to the economy of

the procedures ... it is a means to achieve the research objectives through empirical evidence
that is acquired economically.” 3
According to Peil, “designing a research project involves organizing the collection and analysis
of data to provide the information which is sought.” 4
No single definition brings out the full range of important aspects. From the above though, we
can emphasize the research design as consisting of the plan, which is designed for: -
- Collecting data
- Analyzing the data
- Presenting the findings vis-à-vis the research objectives.
Obviously then, the design ultimately chosen will depend on the study objectives, types of data
required, sources of data and cost.
Classification of Research Designs
Over the years several research designs have been developed, tested and used in various fields.
Various types of research can be seen as an expression of differing research goals: descriptive,
exploratory, casual, experimental, and comparative research provide somewhat different types of
information. Many projects combine two or more of these. Unfortunately, no simple
classification system defines all the variations that must be considered.
Overall, any design can be said to be either quantitative or qualitative. This is based on the
nature of the data they aim at and end up collecting. If the data can be quantified, the design can
be said to be quantitative. If the data to be collected is not of a quantifiable nature, then the
design is said to be qualitative. For example the attitudes of a client towards a credit program
services is largely qualitative.
 Quantitative designs
Some authorities have thus classified research designs as follows:
- Descriptive research
- Casual comparative
- Co-relational research
- Experimental research
 Qualitative designs - Case study

- Historical research
We can classify research design using at least seven other different perspectives.
i. The degree to which the research problem has been crystallized

– Exploratory study
– Formal study
The difference between the two lies in the degree of structure and the immediate objective of the
study. An exploratory study uses loose structures and the objective is to discover future research
tasks. The formal study begins with a hypothesis or question. It involves precise procedures and

data specification of data sources. Its objective is to test the hypothesis or answer the research
questions. The distinction between the two is however not very precise.
ii. According to the method of data collection

- Observational study
- Survey study
In monitoring (which includes observational studies), the researcher looks at the subjects, which
are not asked any questions. For example, observing the actions of a credit group during a
meeting.
In a survey study, the researcher asks the subjects questions and collects their responses.
iii. According to the ability of the researcher to manipulate or produce effects in the
variables under study
- Experimental study
- Ex-post facto study
In an experiment, the researcher is able to control and / or manipulate the variables e.g. to change
them or hold them constant. It is the most powerful support possible for a hypothesis of
causation.
In an ex-post facto design, the researcher has no control over the variables. The researcher can
only report what is happening.
iv. According to the purpose of the study

- Descriptive study
- Casual study
A descriptive study seeks to find out who, what, where, when, or how much - e.g. a study on
delinquency. A casual study seeks to explain relationships among variables. E.g. why
delinquency rates are higher in one branch than the other.
v. According to the time dimension

- Cross-sectional study
- Longitudinal study
- Historical study
A cross-sectional study describes a sample at a particular point in time – a snapshot of the

phenomenon at the time. A longitudinal study describes a sample over a period of time for the
purpose of tracking changes in the samples (same people over a period of time) cohort group
studies (where different subjects are used for each subsequent measurement)
A historical study is a systematic or objective location evaluation and synthesis of evidence in
order to establish facts and draw conclusions about past events.
vi. According to the topical scope

- Case study
- Statistical study
A case study emphasizes a full contextual analysis of fewer events or conditions and their
interrelations. Hypothesis may be used, but the study relies on qualitative data, which makes

testing of the hypothesis more difficult. The emphasis on detail helps to give the researcher
valuable insight for problem solving, evaluation and strategy. In addition, it relies on a multiple
sources of information.
A statistical study is designed for breadth rather than depth. A statistical study attempts to
capture the characteristics of a population by making inferences from a sample’s characteristics.
Here hypothesis are tested quantitatively. If sample is large enough to represent the population, it
is possible to make generalizations.
vii According to the research environment

- Field conditions research
- Laboratory conditions research
- Simulation research
Field conditions studies are those that occur under actual environmental conditions. Laboratory
conditions studies are carried out under laboratory controlled conditions. Simulations arise out of
replicating the essence of a system or process. Examples of simulations: where characteristics of
various conditions and relationships in actual situations are often represented in mathematical
models; role-playing etc.
Some Research Designs for Microfinance
a) Descriptive Design
This is an appropriate design where the study seeks to describe and portray characteristics of an
event, situation, and a group of people, community, or a population. It enables the researcher to
profile the sample or population by gathering complete, and possibly accurate information.
Data for the survey is collected using a questionnaire, although a combination of tools may be
used. A well-structured survey covers personal, special, and economic characteristics of the
subjects.
NB: A historical study can also be used as a descriptive design. This describes past events, e.g.
the development of microfinance in Kenya.
 Portrayal of phenomenon or events fully

Advantages:
 Appropriate for conducting baseline surveys
 Lack of a scope to identify and assess relationships between concepts. Likewise, a hypothesis
Disadvantages:
 Occurrence of errors. Examples: -sampling errors (if sampling method fails to select a sample
on a casual relationship cannot be tested.
which fully represents the population) and measurement error (when data is not measured
accurately).
b) Historical Research Design

This is a systematic or objective location, evaluation, and synthesis of evidence in order to
establish facts and draw conclusions about past events.

Stages
i. Identification and delineation of the problem
ii. Formulate hypotheses/ set of questions/research objectives.
iii. Select data resources- then collect data, organize, verify, validate, analyze, select relevant
data from the main or massive data.
iv. Process data
v. Test the hypotheses/answer the questions
vi. Write the report
Value of historical research

i. Allows answers to current problems to be looked for in the past
ii. It has the ability of employing the past to predict the future.
iii. Ability to use the present to explain the past
Limitations
i. Difficulty of obtaining adequate data and the determination of how much data is adequate.
ii. Modern history argues that there is too much data to choose from; that much of it is not
relevant. The question is what is relevant/authentic
iii. One does not make his own observations – but relies on other people’s observations and data.
These other people are not necessarily trained observers.
Sources of data
Primary sources – e.g. archives, museums, remains or relics of a given period (e.g. skeletons,
tools, buildings); objects/events that have a direct relation with the subject; documents written by
“direct” persons, original minutes etc
Secondary sources – these do not bear direct physical relationship to the event being studied. e.g.
replica of an art object such as copies of original documents
Evaluation
The information gathered should be carefully evaluated or attested. That data accepted will be
historical evidence.
 Authenticity of the source (external criticism)

Criticism
 Accuracy of the data (internal criticism)
c) Exploratory Research Design

This research design seeks to provide new insights and discovery of new ideas to the researcher.
Examples: Community financial need assessment studies.
Stages
i. Formulate research questions that are addresses through a scientific inquiry or investigation
such as a survey.
ii. Literature review, especially in historical surveys
iii. Analyzing data and stimulating cases for new insights
 Leads a researcher top formulate a research hypothesis for further or future researches
Advantages
 Provides for possibilities of doing different types of research.

 Stimulates interest and encourages the attitude of seeking to understand and gain new
insights rather than trying to test a certain research related statement
 Promotes depth ness in seeking for answers and explanation of events and situations as they
take place
 Encourages drawing together various pieces of information and thus increases the
investigative power of the researcher.
d) Experimental Research Design

In experimental research the investigator deliberately, controls and manipulates the conditions,
which determine the events. The researcher makes a change in the value of one variable
(independent variable) and then observes the effect of that change on another variable
(dependent variable)
In microfinance and social research in general, it is not possible to carry out the experiment per
se. However, we may employ something close to it – thus coming up with a quasi-experimental
research.
In a quasi-experimental design, we introduce a number of control groups to ensure internal

validity. This is done to eliminate the possibility of the outcomes being affected by the
experimental treatment. We also seek to guard against threats to external validity such as aging.
Some of the common threats to validity are: -
 History – when one is exposed to the treatment, there is a history of events which may not

affect the outcome
Maturation
 Statistical regression – if the instruments use to measure the outcome are unreliable, which
leads to inaccuracies


Instrumentation – the reliability of the people testing and the testing itself.
Selection – bias in the selection of groups
 Experimental mortality – between time t1 and t2 the residual group may not be related to the
initial group.
Advantages
i. It’s the only design in which a hypothesis is truly formulated and tested
ii. It facilitates the assessment of casual relationship between variables and the degree of that
relationship.
Disadvantages
i. Time consuming and costly – it requires more complicated planning and type of data that is
required
ii. It requires more sophisticated research skills from the researcher.
iii. Measurement error – due to response error and investigator’s bias
Step 6: Selecting the Data Collection Method
Data collection is the process of gathering empirical evidence. The evidence collected helps the
study in getting new insights and thus answer the research problem. Selecting the data collection

method is one of the steps in the data collection process. Data collection consists of the following
steps:
i. Selecting methods of data collection
ii. Preparing and testing data collection instruments
iii. Identifying and selecting people to assist in data collection
iv. Training the research team in data collection
v. Actual collection of data
Alternative Methods of Data Collection

There are a number of data collection methods. For any study, the appropriate method depends
on the research problem, design and the kinds of data required. To complete a study, we usually
need information about a particular group of people or items. This group is known as a
population. The population can be small (e.g. the MDP class), large, (e.g. university students in
Kenya) or even infinite (e.g. volume of water passing under a bridge as long as the river
continues flowing).
Information is collected by means of a survey. There are two types of surveys, namely, census
and sample survey. This gives rise to the two basic data collection methods:
 Census
 Sampling
There are two other methods, which although not usually included in statistical books, are both
 Group discussion (Focus Group Discussion)

useful and relevant in social and communication research. They are:
 Indirect Methods
NB: Many authorities treat those two as techniques rather than methods of data collection
Group Discussion [Focus Group Discussion]

This method is becoming increasingly useful and important in research. This is especially in
social research (e.g. community development, microfinance, entrepreneurship, etc). In such
research contexts, the populations are traditional (or partially traditional) and community-based.
The populations also have patriarchal social structure
Because of the above and other reasons, individual members find it easier to comment on certain
issues under the support and security of groups. In addition, data collection in such situations
requires community leaders who can adequately represent the community.
This method has its unique methodological approach from census and sampling methods
(although it could be classified as a survey method). It is unique in the following ways:
 It is less structured, more informal and interactive and deeper in the method of
enumeration.
 It is relevant and suited to community oriented research
 It uses the representative social and leadership structures existing in the community or
 It covers a whole community, which is a small population on its own merit.

population
 It is used to collect both quantitative and/or qualitative data.
Data may be collected using two types of approaches, namely, participant and non-participant
observation.

Indirect Methods
 Unavailability of individuals who have the data, difficulty and high costs of contacting
These are useful hen data is not available directly form individuals. Reasons for this include:
 Individual with the information but unwilling to provide the data

them
 Individuals with information on past events may no longer be alive
For the above reasons, the researcher has to depend on indirect sources of data (secondary
sources). Examples of such sources are: -
- Hearsay stories
- Written documents/ books
- Original/ copies of handwritten notes, minutes, etc
- Content analysis of a text and images (e.g. words, frequency of mention, pictures,
appearances, spaces and position).
Census
If every number or item of the population called a unit is surveyed, this is known as a census. A
census is conducted with definite objectives, which may be both general and specific
This method should be selected only when there’s need to have information on every member in
the population. In this way, the method has the advantage of being comprehensive
 It requires a wide administrative organization

Limitations
 It needs a large number of personnel

 It is costly
 It requires a lot of time
 The error in measuring population by counting each item is increased in proportion to the
population size
Sampling (Sample Survey)

When a survey covers less than 100% of the population, it is known as a sample survey.
The individuals selected collectively make up a sample. The selection of individuals is done in
such a way that the sample represents the population adequately.
Example: If an MFI wants to find out the opinion of the clients on its pre-loan training program,
it may not be necessary to get the opinion of every client. A representative sample would be
more appropriate.
Sampling Frame
For using sampling method in data collection, it is essential to have a frame of all the sampling
units belonging to the population to be studied with their proper identification and particulars.
Such a frame is called sampling frame. It may be a list of units with their identification and
particulars or a map showing the boundaries of the sampling units.
In selecting the sampling units, the researcher needs to know the size, spread and characteristics
of the population being studied.

Example:
An MFI wants to determine how popular a newly introduced product is with the clients. Suggest
a possible frame for the survey.
Solution:
The MFI decide to concentrate its surveys on credit groups in urban areas only. In this evaluative
research, the unit of measurement is an individual client. To draw a sample, the researcher may
compile a sampling frame, which includes the following units:
 List of credit groups in urban areas
 List of clients in credit groups in urban areas
 List of names o leaders of credit groups in urban areas.
Samples will then be drawn from each of the lists to collect the opinion of a cross-section of the
clients
 Greater economy – more efficiently in terms of the number of personnel, time, and cost
Advantages of Sampling
 Requires a smaller organization

 Shorter time lag
 Greater scope
 Higher quality of work
 Actual appraisal of reliability – you can use the data to account for each observation
Sampling Methods
There are two sampling methods, probability and non-probability. In probability sampling
methods, each individual in the population has an equal opportunity of being selected. This norm
is not observed in non-probability sampling methods. Sampling methods under each category are
summarized in the table below:
Probability Sampling Methods Non-probability sampling methods

a. Random Sampling a Convenience sampling
b. Systematic Sampling b Quota sampling
c. Stratified Sampling c Purposive/Judgment sampling
d. Cluster Sampling d Snowball sampling
e. Stage (multi-stage) Sampling e Dimensional sampling
Probability Sampling Methods

a) Simple Random Sampling
Every subject has an equal chance of being selected. It may be with or without replacement.
Sampling where each item may be chosen more than once is called sampling with replacement.
Where each item may not be chosen more than once is called sampling without replacement.
NB: Each time when a subject, who is selected, is not replaced, the chance of selection changes
in the successive selections especially in small populations
b) Systematic Sampling
This is a modified random sampling
i. List the population in some order e.g. alphabetically or in the order or registration, etc
ii. Obtaining a random starting point
iii. Choose every kth number from the list

Example:
Describe how to choose a systematic sample of 30 from a population of 100 items
Solution:
i. Establish the gap – by 100/30 = 3.3. Thus, every time we select an item, we need to move 3.3
places along the list.
ii. Decide on the random starting point. - It should be between 1 and 3.3 inclusive. Assume we
chose 2.
iii. Select the sample:
1st = 2nd item
2nd = 2+3.3 = 5.3: choose 5th item
3rd = 5.3+3.3 = 8.6 choose 9th item
4th = 8.6+3.3 = 12 choose 12th item
5th = 12+3.3 = 15.3 choose 15th item. Etc
 Easy to use
Advantages
 Easy to check for errors
Disadvantages
There may be a periodic cycle within the frame itself.
E.g. if every 10th item produced by particular machine is faulty, and the kth item coincides with it,
then you will end up with a “poor” sample.
To check on this, you use the advantage above, i.e. choose another starting point.
c) Stratified Sampling
i. Here you first divide the subjects into homogeneous groups (e.g. males, females). These
distinguishable layers or groups are called strata. Other samples of strata are branches,
regions, urban/rural, etc.
ii. Separate random samples are then taken from each of the strata and put together to form the
sample from the population. The random strata from each sample can be selected using
simple random or systematic random sampling.
Exercise:
A certain MFI has 160 credit officers, 40 secretaries, and 20 drivers. It is required to select a
committee of 11 to represent all the employees. Describe how this selection might be made in
order to give as close a representation as possible without any bias towards the individuals.
Note: Provided that the population can be split into distinguishable strata, a stratified sample
would be more precise than the simple random sample.
d) Cluster Sampling
Sometimes there is a neutral sub-grouping of the population called clusters. e.g. if the population
consists of all children in the country attending public primary schools, then the local education
authorities form natural clusters.
Cluster sampling is thus meant for large populations, which are widely dispersed. To select the
sample, you randomly select the clusters and then survey all the subjects within the captivity, i.e.
the selected clusters.

Unlike the stratified sampling where the population is stratified according to some criteria,
cluster sampling involves selecting clusters that are heterogeneous. This method aims at
minimizing expenses related to selection procedure and interviewing.
e) Stage Sampling (Multi-Stage Sampling)

This is an extension or variation of the cluster sampling. It involves selecting clusters and then
randomly selecting individuals within clusters. This is because it would be extremely expensive
in certain cases to interview all subjects in the selected clusters. It is also useful where the
population has a clearly defined hierarchical administrative or bureaucratic structure.
Non-Probability Sampling Methods
a) Convenience Sampling
Here the sample is selected based on the ease of access in terms of speed and low cost. It is
therefore a mere accidental selection of the nearest individuals to serve as respondents. e.g.
captive audience likes students, lecturers, microfinance clients, etc. another example is when
journalists seek a quick opinion of a few members of public or callers (radio/TV)
b) Quota Sampling
This is a non-probability equivalent of stratified sampling. Here, you obtain representation of the
various elements of the total population in the proportion in which they occur there.
First the population is divided into groups in terms of age, sex, and income level, and so on.
Then, the interviewer is told how many people to interview within each specified group but is
given no specific instructions about how to locate them and fulfill the quota.
 It is quick to use
Advantages
 Complications are kept to a minimum.

 Unlike random sampling, any member of the sample can be replaced by another with the
same characteristics. Thus there’s no randomness – we don’t know how these people will be
chosen. (However, this can also be taken as a disadvantage/limitation because of the
likelihood of bias)
c) Purposive Sampling/Judgment Sampling

This is handpicking the cases to be included in the ample on the basis of your judgment of their
typicality; i.e. building a sample that is satisfactory to the specific needs. This non-probabilistic
method sampling has a specific purpose which closely resembles the convenience sampling. In
purposive sampling though, samples are selected using set criteria e.g. whether the credit group
is men only, women only, or mixed. This method is often used for community studies 0r case
studies.
d) Snowball Sampling
Here you first identify a small number of individuals who have the required characteristics. After
that, you use them as informants to identify others who qualify for inclusion. These in turn
identify yet others,

e) Dimensional Sampling
This is a further refinement of quota sampling. Here you identify various factors of interest in a
population and obtain at least one respondent for every combination of these factors.
NOTE: For statistical significance, use samples greater than 30
Problems of Sampling
Some of the problems related to sampling methods are: -
 Lack of technical expertise, especially on the use of random methods
 Absenteeism of the respondents
 Non-cooperation of the respondents
 Low response especially in mail survey
Step 7: Selecting the Survey Method
The basic types of survey methods are: -

 Eye survey
 Interview
 Mail survey
 Self-administered questionnaire
Eye Survey
This is a method, which is relevant to a research context where no direct response is required
from the subjects. It is a method appropriate to an observation design. Eye observation is made
 Count the number of subjects

to: -
 Count of the frequency of occurrence of an activity/event

 Make an eye estimate
 It is quick
Advantages
 It is easy to carry out

 It is economical
 Doesn’t require personnel with high technical skills
 Not useful when detailed data is required

Limitations
Interview
Interview method can be structured or semi-structured. In a structured interview, questions are
exact. In a semi-structured interview, the interviewer uses an interview schedule as a guide to
data collection. Interviews are of two types – personal and telephone
Personal Interview
The interviewer collects data directly and personally from the respondents
 Chance to probe and clarify responses

Advantages
 Allows for detailed descriptions and comprehensiveness

 A good rate of return

 Bias in response – e.g. if respondent doesn’t have confidence in the interviewer
Disadvantages
 Inaccurate responses to personal or sensitive questions

 Bias from the interviewer, e.g. because of the manner in which questions re asked.
Telephone Interview
This is a direct method, although it is not face-to-face.
 Efficient in terms of time and data analysis

Advantages
 Useful for quick collection of opinions.
 Locks out people who don’t own phones

Disadvantages
 Relatively impersonal – no face to face interaction

 Time – may be inadequate for respondent.
Mail Survey
A survey questionnaire is sent to the selected respondents. it is very ideal within organizations. It
is a convenient and easy to use method. It is also time and cost effective
 Subject to availability of mailing list

Disadvantages
 Useful only with a literate population
Self Administered Questionnaire

A questionnaire is given to each respondent to fill. The interviewer carries it out personally and
 Easy to implement
directly. Some of its advantages are: -
 Respondents can ask for clarifications
 Possibility of interviewer influencing the responses

Disadvantages:
 Needs many interviewers/field assistants

 Thus could be quite expensive.
Step 8: Preparing Data Collection Instruments
A data collection instrument is the tool used by the researcher to collect the required data from
the respondents. The most commonly used tools are:


Interview guides

Observation guide
Questionnaire
Questionnaire Design Process

1. Specify the needed information. This requires you to review the research problem and
review the research questions/objectives/hypnosis. You also need to have a clear
understanding of the target population

2. Specify the interview method to be used – personal, telephone, or mail interview
3. Determine the content of the individual questions. Include only the questions that are
relevant. Every question you ask should contribute to information needed or serve some
specific purpose.
Neutral questions should be placed at the beginning of the questionnaire to help in
establishing a rapport with the respondent.
Filter questions may also be used. e.g.
a. What products do you sell?
b. If you sell product A, go to question no _
4. Design the questions to overcome the respondents’ inability to answer. They must be
clear.
5. Decide on the question structure – open-ended (unstructured), closed-ended (structured)
or a combination of the two. Open-ended questions help respondents to express
themselves and are very easy to formulate. However they are the most difficult to
analyse.
6. Determine the wording of the questions. A simple guideline for doing so is;
Use simple vocabulary
Avoid ambiguity
Avoid double-faced questions e.g. “Do you want to leave your current spouse and marry
another one?”
7. Arrange the questions in the proper order (i.e. in the order you want them to be
answered)
8. Identify the form and the layout of the questionnaire e.g. margins, spacing, fonts, leave
enough space for one to write. For the closed questions, use the same forms. e.g. options
arranged vertically or horizontally. Number all questions and provide boxes for marking
responses.
9. Reproduce your questionnaire
Enough copies fro pre-testing
Pre-test
Modify the questionnaire
Enough copies for the final study
How to Minimize Ambiguity

1. Ensure vocabulary is simple, direct, and familiar to all the respondents.
2. Don’t use technical jargon on non-technical people.
3. Avoid words that mean different things to different people
E.g. College, “volunteer”, “mkubwa”
4. Avoid words with vague or ambiguous meaning. Give the respondent an adequate frame
of time reference to interpret the question; else he will have difficulties in interpreting.
You’ll also find it difficult to analyze. E.g. Often Occasionally
5. Avoid words that will embarrass the respondent. e.g. “Have you stopped beating your
wife?” Use a disguised question instead
6. Avoid leading questions, e.g. “The girl-child is disadvantaged, don’t you agree?”
7. Avoid instructions that are potentially confusing, e.g. lengthy instructions.
8. Ensure that all the questions are applicable to all respondents; else ask filter questions e.g.
“Which credit program were you in before joining this one?”

Pre - Testing/Piloting the Questionnaire
A questionnaire is pre-tested to identify any deficiencies so that they can be corrected before the
 Be open-minded; open to criticism

main study. When pre-testing: -
 Select the pre-test sample carefully

 Ensure the sample size is appropriate – not too large, but with all the sample groups
 Use personal interviews

represented.
 Give clear instructions to the respondents
After pilot testing, re-do the questionnaire. Ensure that the final one has the following areas
 Identification – serial number, name of interviewer, name of respondent, date of

covered:
 Background information – age, sex, etc

interview.
 Factual information – in relation to the research questions

 Opinion/ attitudes
Actual Data Collection

If research assistants are to b used, they should be thoroughly trained. You should also get the
authority to carry out research (from the office of the president, KICC 7th floor). In addition the
following fieldwork guidelines will be useful:
1. Asking questions – follow the order in which they appear, use the exact words in the
questionnaire, repeat questions that are not understood and probe the respondent where
necessary.
2. Record responses as you do the interview to avoid forgetting
3. Use the respondents words as much as possibly
4. If using research assistants:- supervise them; ensure procedure of research is followed;
administer some questionnaires (as control); collect and edit their questionnaires daily;
keep a record of hours worked by each; control the assistants (o follow sampling plan,
daily records of areas covered/interviews done, control cheating, get their opinion on the
research, etc)
5. Ensure interviews are of good quality – appropriate introduction, precision when asking
questions, probing, handling defiant/hostile respondents, terminating interview
effectively.
6. Avoid data collection errors, which may arise out of suspicion, inaccurate responses.
These may be caused by the first impression, time pressure, fatigue, long questionnaire,
fraud & deceits, etc.
Step 9: Selecting Data Analysis Tools
The tools that will eventually be used for analyzing data are selected during the research
planning stage and not after data has been collected. The preliminary plan for data analysis helps
the researcher in deciding on the following:
i. What to do when
ii. How questionnaires will be checked for completeness
iii. Action to take after the checking – e.g. reject some questionnaires or questions (e.g. due
to omission of some issues, etc.)
iv. Editing the questionnaires – identifying illegible questions, incomplete responses,
unsatisfactory responses, ambiguous responses etc.

v. Options to pursue after rejection: - e.g. returning to the field, assigning missing values,
discarding the unsatisfactory questionnaire, excluding the questions with unsatisfactory
responses from analysis.
vi. Statistical methods to apply in the analysis.
vii. Procedure to follow in analysis – coding scheme, code sheet, tabulation.
Statistics and Data Analysis

Statistics is a science of numbers; a discipline that provides the tools of analysis in research.
They are the techniques used in collecting, describing, analyzing, summarizing and drawing
conclusions on the data.
For our purpose, we shall define statistics as the collection, analysis, and interpretation of
numerical data. Data in this case are the figures collected, or a series of observations
Types of Statistical Methods

There are two types of statistics - descriptive and mathematical/inductive statistics.
1) Descriptive Statistics
Deal with compilation and presentation of data in various forms e.g. tables, charts, and diagrams.
This is done to display and pass on information from which conclusions and recommendations
can be made.
Functions of Descriptive Statistics

a) Measuring
Since concepts (characteristics) have theoretical definitions, it is important that we define them
operationally. Measurement is defining a concept operationally in tangible terms. Any data set
has concepts that need to be defined operationally to make them measurable. e.g. a microfinance
client may be defined operationally as “ a duly registered person, saving consistently, attending
group meetings…”
A variable may be measured at different levels – Nominal, ordinal, interval and ratio.
Nominal measures
Name/label e.g. gender, type of client, etc. from these nominal variables we could have the
category labels “male & female” and “start-up & expansion” respectively. It then becomes
possible to group the population into homogeneous categories and providing a count of each
category. Furthermore it becomes possible to compare two or more homogeneous categories
of nominal values
Accessed a Type of client

Loan?
Existing Start up
Yes 55 60
No 65 80
TOTAL* 120 120
* Assuming a sample of 120 clients
Ordinal measures
Here, each individual or unit has a position in a numbered order. e.g.
1. Never
2. Sometimes

3. Always
Each category has a number as a label
Interval measures
Here it is possible to rank the individuals or units and also measure the distance between
them. Therefore, we need a physical unit of measure.
e.g. the no. of loans accessed
Ratio measures
A variable is taken to be a ratio level if the scale of values assumed by the variable includes
an absolute zero value, i.e. 0 – 100%
b) Quantifying
In describing a certain characteristic from a set of data, it is necessary to represent its value in
terms of quantities or numerical values. e.g. we can assign male (1) and female (2). This is called
coding.
c) Organizing data
Data should be organized in a way that makes it easy for the mind to absorb and understand. To
organize data is to arrange them into a pre-set format. This ultimately helps in describing the
situation through numbers and representing it through diagrams.
The number of times of the occurrence of a variable is the frequency
Simple frequency distribution

Example: No of visits by a branch manager to 10 credit groups is given as:
8, 6, 5, 5, 7, 4, 5, 7, 9, 4
i. First arrange them in ascending (or descending) order:
4, 4, 5, 5, 5, 6, 7, 7, 8, 9
ii. Then put them in tabular form
No of visits (x) Tally No of groups

[variable] (frequency = f)
4 II 2
5 III 3
6 I 1
7 II 2
8 I 1
9 I 1
iii. Plot the frequency distribution

Table 1: Simple frequency distribution
x f
4 2
5 3
6 1
7 2

8 1
9 1
The researcher is thus able to see how the numbers of visits are distributed
Group Frequency Distribution

Sometimes, the spread of the data is very large
Example: (These could be no. of products [variable] stocked by 100 small scale retail stores)
81 85 62 71 70 81 86 67 96 51
63 71 75 69 48 34 87 86 73 75
42 91 58 93 52 82 90 95 82 72
53 38 77 93 85 47 70 68 57 71
96 40 70 92 68 88 58 51 90 74
52 63 96 77 83 76 48 92 81 83
92 73 84 78 78 72 60 84 78 60
43 70 83 64 96 93 55 73 58 40
88 96 72 53 87 92 73 77 63 58
71 80 38 63 56 76 82 61 76 63
i. You may first arrange the variables in ascending [or descending] order in order to
identify the smallest and highest values.
ii. We condense the products by allocating them into CLASSES. (We can use groups of 10
e.g. 1 – 10, 11 – 20, etc. each group is called a class).
iii. Use a tally mark to place each variable in its appropriate or corresponding class.
iv. The frequency distribution is constructed as shown below:
Table 2: Group frequency distribution
No of products Tally No of stores

(variable =x) (frequency = f)
31 – 40 IIII 4
41 – 50 IIII 5
51 – 60 IIII IIII IIII 15
61 – 70 IIII IIII IIII I 16
71 – 80 IIII IIII IIII IIII IIII 24
81 – 90 IIII IIII IIII IIII I 21
91 - 100 IIII IIII IIII 15
Total 100
NOTE:
In constructing group frequency distribution, it is important to calculate the class interval. Class
interval = upper class boundary, less lower class boundary.
To get lower boundary: lower class limit less 0.5
= 31 – 0.5 = 30.5
To get upper boundary: upper limit plus 0.5
= 40 + 0.5 = 40.5
Therefore the class interval = 40.5 – 30.5 = 10

d) Displaying Data
Descriptive statistics also help us in displaying data. We can use tools like histogram, bar charts,
cartoons, pie charts, frequency curves, etc to display data.
i) Cartoons
One can chose cartoons to display data. For example
Men Women
1 rep: 1000
ii) Bar Charts (Discrete Data)

This useful for discrete data
Y-axis
(Frequency)
X-axis
0 1 2 3 4 (score or observation)
Note
i. All bars are of equal width
ii. The height of each bar represents the frequency (sometimes percentage)
iii. The bars are separated to show the fact that the data is discrete
iv. Axes are scaled or labeled and the bar chart titled
v. The first bar can touch the y-axis.
iii) Histogram (continuous data)

This is suitable for continuous data e.g. age, weight, etc
i. The bars touch each other to indicate the continuous nature of the data.
ii. The score is not indicated in the middle but at the beginning of the bar.

Frequency
Observation/score
iv) Pie Chart

A pie chart is circular. The angle of each sector is proportional to the corresponding frequency
Example:
The following diagram shows how different regions share the total loan amount disbursed by an
MFI.
A B
800
D
1200 C 700
If the total loan disbursed to region A was Ksh 600,000/=, calculate: -

i. The total loans disbursed, and
ii. The loan amount disbursed to each of the other regions
2) MATHEMATICAL/INDUCTIVE/INFERENTIAL STATISTICS
This is concerned with extending beyond particular information available and attempting to
make general predictions. They are measures that enhance the understanding of data. The
 Measures of central tendency (averages)

important statistical measures used are:
 Measures of dispersion
 Measures of correlation
 Measures of association

MEASURES OF CENTRAL TENDENCY
Collected data is useless and meaningless until it is organized in a certain manner. A measure of
central tendency is an aggregate or summary measure that represents a value that is at the center
of the distribution values.
a) Mean (Arithmetic mean)

This measure is arithmetical average of a distribution of values.
The arithmetic mean (AM) is denoted by x, where x represents a variable with a distribution of n
values x1, x2, and _ _ _ xn. It is worked out as = sum of observations = ∑x
No of observations n
Example:
Mean of raw data: Suppose you collected the following data on number of members of 5 credit
groups: -
30, 26, 20, 29, 20
The average number of members per group (mean) = 30+26+20+29+20
5
AM or x = 125/5 = 25
Mean of a frequency distribution

In case of a large distribution of values, the distribution of variable x takes the form a frequency
distribution. Then you use a formula to calculate the mean. X = ∑fx
∑f
Example:
The following data shows the visits by a credit officer to 15 credit groups.
4, 1, 3, 6, 7, 2, 2, 8, 2, 7, 2, 5, 5, 9, 5
No of visits Frequency Fx
(value of x) (groups visited
f)
1 1 1
2 4 8
3 1 3
4 1 4
5 3 15
6 1 6
7 2 14
8 1 8
9 1 9
TOTAL ∑f = 15 ∑fx = 68
Substituting:
X = ∑fx = 68 = 4.5
∑f 15

Mean of a grouped distribution
If the data is grouped, we modify the frequency distribution table to work out the mean.
Example: If the data provided is as follows: -

No of visit (x) Frequency (groups
visited f)
1–3 6
4–6 5
7-9 4
TOTAL 1515
NB: We cannot work out the fx because x is not a single figure. We therefore need to work out
the class midpoints.
E.g. for class 1 – 3, the class mid point will be (1 + 3)/2 = 2
No of Class Frequency fx
visits midpoint (groups
(x) visited f)
1–3 2 6 12
4–6 5 5 25
7–9 8 4 32
∑f = 15 ∑fx =
69
x = ∑fx = 69 = 4.6
∑f 15
 The value that occurs most often. It is therefore the value with the most frequency.
b) Mode
Example: What is the mode of the following data?

4, 1, 3, 6, 7, 2, 2, 8, 2, 7, 2, 5, 5, 9, 5
 It is quite commonly used measure of central tendency by research students
 For grouped frequency distribution, the mode is the mid-point of the class with the
NOTE:
 If a distribution has the same frequency for all values, such a distribution has no mode.
highest frequency.
c) Median:
The middle value when all values are arranged in the order of size. It divides the distribution into
two equal halves of number of values on its either side.
Example: What is the median of this data?
4, 1, 3, 6, 7, 2, 2, 8, 2, 7, 2, 5, 5, 9, 5
 Re-arrange: - 1, 2, 2, 2, 2, 2, 3, 4, 5, 5, 5, 6, 7, 7, 8, 9



If total number of values is odd, take the middle value as median
If it is even, calculate the average of the two middle numbers.
 Write in columns: -
Median of ungrouped frequency distribution
i. The values of the variable (x)
 Have a column for the cumulative frequency

ii. The frequencies
e.g. frequency distribution of schools visited
Score / no of Frequency (f) Cu. f (F)

visits (x)
1 1 1
2 4 5
3 1 6
4 1 7
5 3 10
6 1 11
7 2 13
8 1 14
9 1 15
Total ∑f = 15
 Locate the middle data item by n/2; where n is the total number of observations (∑f)
n/2 = 15/2 = 7.5
 Calculate the cumulative frequencies until they reach the value 7.5 or exceed 7.5 for the first

time
Choose the median as the value of x corresponding to the last value of F found to exceed 7.5.
This is 10, and the x value that corresponds to it is 5. Therefore the median = 5
Median of grouped distribution

Example
No of visits Frequency Cu.f
(x) (f) (F)
1–3 6 6
4–6 5 11
7–9 4 15
∑f = 15
 n/2 = 15/2 = 7.5.

7.5 should be lying in the class with the cu.f of 11 [this is 4 – 6]
 Then use the formula:
Median = U + (1/2F – C)w

N
Where: U = the upper limit of the median class
F = Total frequency

C = Cumulative frequency up to but not including the median class
W = Class interval
N = the frequency of the median class
Therefore, median = 6 + (1/2 x 15 – 6)3 = 6+(7.5 – 6)3

11 11
= 6 + (4.5) = 6 + 0.409
11
= 6.4
Measures of Dispersion
A measure of dispersion is an aggregate measure of deviation from a central value. The most
commonly used measures are the:
i. Range
ii. Mean deviation
iii. Standard deviation
The Range
The difference between the lowest value and the highest value in the distribution
Example: Given the following sets of data, calculate the range
Set A: 1, 2, 3, 4, 5, 6, 7, 8, 9
Set B: 3, 4, 4, 4, 5, 5, 6, 6, 7
Answer:
Set A: 9 – 1 = 8
Set B: 7 – 3 = 4
This shows that the values in set A are spread out more than those in set B.
Variance and Standard Deviation
Deviation is the difference between the value of an observation and the mean, i.e. (x – x).
The deviation can be from the mean, mode or median. In most cases it is from the mean.
(Where you are not told, assume it is in reference to the mean)
Illustration:
Given the data – 1, 2, 2, 6, 9, determine the mean and deviation.
a) Mean = 20/5 = 4
b) Deviation (how far each value is from the mean):
_ _
X x x–x
1 4 -3
2 4 -2
2 4 -2

6 4 2
9 4 5
_
∑(x -x) = 0
To get the deviation for the whole distribution: -

_
= ∑ (x - x) = 0
n 5
To avoid getting zero (0), which does not tell us anything, we can make use of: -
i. Absolute values |x|, or
ii. Square the differences and sum them
Using the squaring method: -

_ _ _
X x x-x (x – x)2
1 4 -3 9
2 4 -2 4
2 4 -2 4
6 4 2 4
9 4 5 25
_
∑ (x - x) 2
=
46
_
The magnitudes of deviation will change e.g. -3 becomes bigger (9). [If we had any of values (x -
x) being positive but less than 1, the magnitude of the deviation would become smaller. e.g. 0.4,
after squaring, would become 0.16]
Therefore, we divide by the number of the observations:
_
∑ (x - x) 2
n
The result is the variance
Formula: _
Variance = δ2 = ∑ (x – x) 2
n
= 46
5
= 9.2
If we get the square root of the variance, (i.e. √δ2), the result is the standard deviation.
Therefore: _
Standard deviation = √δ2 = √∑ (x - x) 2
n
_
= δ2 = √ ∑ (x - x) 2
n
= √9.2
= 3.03

NOTE: A shorter (and simpler) method
_
Variance: δ = ∑ (x - x) 2
2
n
_ _
Expanding the equation = ∑ (x2 - 2xx + x2)
n
_ _
= ∑x2 - 2x2∑x + nx2
n n n
_ _
= ∑x2 - 2x2 + x2
n
_
= ∑x2 - x2
n
Thus using the formula and the data given:

x x2
1 1
2 4
2 4
6 36
9 81 _
∑x 126
2=
and x = 42 = 16
2
Substituting: Variance δ2 = ∑x2 - x2 = 126 - 16

n 5
= 25.2 – 16
= 9.2
Standard deviation √δ2 = √ 9.2

= 3.03
Measures of Association
a) Rank Correlation Coefficient (Rs)
The rank correlation investigates the presence or absence of association between variables.
Moreover, it measures the strength or degree of relationship between variables.
Assumptions
i. The data consists of a random sample of n pairs. Each pair of observation represents two
measurements taken on the same object or individual called the unit of association.
ii. Each x (observation) is ranked relative to all other observed values of X (variable e.g.
age) from smallest to largest or the largest to smallest in order of magnitude.
E.g. X Rank
3 4
6 1
4 3
5 2

iii. Each y (observation) is ranked to all other observed values of Y (variable e.g. height)
from the smallest to the largest or the largest to the smallest in order of magnitude
iv. If ties occur among the x’s or among the y’s, each tied value is assigned the mean rank
position for which it is tied.
Example 1
X Rank Positions
3 1 1
6 5 5
4 2 2.5
4 3 2.5
5 4 4
For tie ups = 2+3 = 2.5
2
Example 2
X Rank Positions
3 1 1
6 2 3
4 5 5
4 3 3
4 4 3
For tie ups = 2+3+4 = 3
3
v. If the data consists of non-numeric observations, they must be capable of being ranked as
described above.
E.g. above average, average, poor, etc
Formula:
rs = 1 - 6 ∑d2i
n (n2-1)
Where di = is the difference between the ranks assigned to xi and yi.

n = is the number of observations
Example:
The following are the number of hours, which 10 clients with loans spent in the business per day
and the number of different customers that they served. Calculate rs.
No of hrs No of diff
X customers Y
8 56
5 44
11 79
13 72
10 70
5 54
18 94
15 85
2 33
8 65

Solution:
Rank of X Rank of Rank xi – rank di2
Y yi (di)
6.5 7 -0.5 0.25
8.5 9 -0.5 0.25
4 3 1 1
3 4 -1 1
5 5 0 0
8.5 8 0.5 0.25
1 1 0 0
2 2 0 0
10 10 0 0
6.5 6 0.5 0.25
n = 10 n = 10 ∑ di2 =
3
Substituting: rs = 1 - 6∑ di2
n(n2-1)
= 1- 6(3)
10(100-1)
= 1- 18
990
= 0.98 (means that they are highly correlated)

Note:
rs ranges from -1 to +1. i.e. –1 ≤ r, ≤ 1
If the value of r s calculated tends towards 0, it shows that there’s no correlation; if towards 1,
there is a correlation. We can go ahead and test whether the above finding is actually true
statistically. For a layman, 0.98 means that the two variables are highly correlated. A
statistician/researcher would like to go further and test whether there is or there isn’t a
correlation between them – hypothesis testing.
Step 10: Report Writing and Dissemination Of Results
This is the final and perhaps the most important step in the research process. Without a report,
the whole project is a waste of resources, as it has no results.
a) Organization
A research project is organized in five major sections – introduction, literature review,
methodology, and findings and conclusions & recommendations. The organization of
academic research reports is guided by the format provided by the concerned institution.
b) Form
Conventions for presentation of tables, footnotes, and bibliography vary. The forms
chosen should be used consistently.

Tables: A table presents numerical data to show relationships between variables. Every
table should be discussed and its contents analyzed. Every table should have a number
and a title. The title can start at the left margin or be centered. Indicate the source
immediately under the table. No source is given if the table is original. Percentage labels
must always show the number on which the per cents are based (N); non-responses
should be omitted from the table
Conclusions and recommendations: Conclusions should be drawn in response to the

research questions/objectives. Recommendations are then made based on the conclusions.
References: indicating the sources shows that you did your homework. Fit the reference
into the text by giving name of the author, date of publication and page number. Peil
(1995:162) emphasizes that plagiarism reflects badly on someone and it may be severely
punished.
The bibliography lists, in alphabetical order by the author, all the works that have been
referred to. The order of listing is author, date, title, and place and publisher for books or
volume and pages for articles.
c) Style
Be accurate, brief, and observe clarity. Avoid dogmatic statements and broad
generalizations.
Avoid the first person (I/we).
No sentence should be longer than three lines.
No sentence should be more than two dependant clauses.
d) Presentation
Numbers over ten, and all percents are usually given as numerals while lower numbers
are written out except where the sentence has many numbers.
If the first word of a sentence is a number, it should be written out.
Decimals should not be used in the text (round them up to the nearest percent instead).
Use commas, semi-colons, colons, dashes and parentheses to make the meaning clear.
e) Publication/Dissemination
The research project work is not undertaken just for the researcher’s benefit. Rather, it
should also contribute to knowledge. For undergraduate academic research projects,
publication may not be necessary. However, you need to make three copies (one for the
examiner/department, the supervisor, and yourself).
REVIEW ASSIGNMENTS
1. Explain Ways of identifying a research problem?
2. List the characteristics of a good problem statement?
3. List the characteristics of good hypotheses?
4. Differentiate between a null and alternative hypothesis?
5. In your area of specialization, choose a research project and identify the following:
(i) The problem statement
(ii) The purpose statement
(iii)Objectives
(iv) Hypotheses
6. Discuss the importance of literature review
7. Choose the topic of interest and write a three page literature review

8. List four indicators of a good review a good review of literature
9. Differentiate between descriptive and inferential statistics?
10. What are the assumptions of rank correlation co-efficient?
11. What are the functions of descriptive statistics?
12. Write short notes on the following:
(i) Measures of central tendency (averages)
(ii) Measures of dispersion
(iii)Measures of correlation
(iv) Measures of association

LESSON THREE: INTRODUCTION
3.1 Chapter One: Introduction
Chapter 1 serves to introduce the problem and the purpose of the study. It acquaints the reader
with the problem. The following areas of discussion are frequently included as subsections in the
introduction chapter.
 Background of the problem
 Statement of the problem
 Purpose of the study or general objective
 Research questions or specific objectives or hypotheses
 Importance or justification or rationale of the study
 Scope of the study
 Chapter summary
3.1.1 Background of the Problem
In this section, the researcher defines the context of the study by providing a brief discussion of
key theoretical approaches and findings reported in earlier related studies. Trends related to the
problem, unresolved issues and social concerns are discussed. Authoritative sources or citations
should be provided in the section.
3.1.2 Statement of the Problem
The problem statement describes the need for the research project in terms of the knowledge gap
to be filled. The researcher should present a clear and precise statement that indicates the gap
that previous research studies have not addressed. Authoritative sources or citations should be
used to support the problem statement.
3.1.3 Purpose of the Study or General Objective
In this section the major research objective is addressed. The purpose statement should
emphasize practical outcomes or products of the study. For example, “The purpose of this study

was to determine (measure, examine, or evaluate) factor that influence the growth of
Microfinance industry in Kenya”.
3.1.4 Research Questions or Specific Objectives or Hypotheses
Specific research questions to be answered or specific objectives to be investigated should be
stated. Either the research questions or specific objectives may be stated. However, most often
research questions are preferred. The research questions need to be broad enough to allow further
breakdown into questionnaire or interview guide items for the data collection. On the average 3-
5 research questions are sufficient. The hypothesis should be stated if the study involves
experimental designs or statistical tests.
3.1.5 Importance or Justification or Rationale of the Study
In this section the researcher describes the values or the benefits that will accrue from doing the
study. The significance of the study is concerned with the relevance of the problem both to the
practice and theory. That is, does the study explore an important question, meet a recognized
need or make a useful contribution to practice and theory. Much value is placed on doing
research, which has primary value for the solution of practical oriented business problems.
3.1.6 Scope of the Study
In this section, the researcher describes the focus or scope of the study to enable an enthusiastic
reader to make generalization of the findings. The scope should address the limitations of the
research in terms of geographical coverage, population or subjects, and time period involved.
The limitations should not be stated in terms of time or financial resources constraints.
Researchers are expected to plan and implement research projects within the available time and
financial resources.

3.1.7 Chapter Summary
A synopsis of the major contents of chapter one including the purpose, justification, and scope
should be presented. A brief description of the remaining chapters of the project should also be
provided at this stage.

LESSON FOUR: LITERATURE REVIEW
4.1 Chapter Two: Literature Review
The literature review section should present a review of the literature related to the problem or
purpose of the study. The section should therefore be organized or structured according to the
research questions or specific objectives in order to ensure relevance to the research problem.
The literature review examines recent (at most 10 years) research studies, company data or
industry reports that act as a basis for the proposed study. Literature review is meant to give the
reader an overview of previous relevant contributions to the problem so that they can better
understand the research problem and methodology to be used in the study.
Specifically, the purpose of literature review is to:
• Help eliminate duplication of what has been done.
• Provide a clear understanding of existing knowledge base in the problem area.
The literature review should be based on authoritative, recent, and original sources such as
journals, books, thesis or dissertations. The section should end with a summary of the important
aspects discussed.

LESSON FIVE: RESEARCH METHODOLOGY
5.0 Chapter Three: Research Methodology
Research methodology section describes the methods and procedures used to carry out the study.
This is an important section, which has direct influence on the findings of the study. Hence, the
methodology used should be described very clearly so that another researcher can follow the
procedures used to reach similar conclusions without difficulty.
The methodology chapter should include the following subsections:
 Introduction
 Research design
 Population and sample
 Data collection methods
 Research procedures
 Data analysis methods
 Chapter summary
5.1 Introduction
The chapter should start with a brief introduction highlighting the general methodology and
organization or structure of the chapter.
5.2 Research Design
In this section, the researcher should identify, define, and provide justification for the specific
research design or strategy used in carrying out the study. Research designs include
experimental, exploratory, descriptive, causal, or case study.
In descriptive studies, survey or case study, the emphasis is placed on defining the design,
revealing its merits and providing justification for its selection. In experimental study, the tests,
equipment and control conditions should be described. The researcher should also define the

dependent and independent variables studied, the procedures used to examine the variables and
steps taken to control for extraneous influences that might threaten the findings of the study.
5.2.1 What is a research design?
A research design is a master plan/ framework or blueprint specifying the methods and
procedures for collecting and analyzing the needed information (Zikmund 2003). It specifies the
details of the procedures necessary for obtaining the information needed to structure or solve the
marketing research problems. The research design also specifies the research methods chosen
determine the information needed as well as define the sampling method, sample size,
measurement and data analysis processes (Kinnear, Taylor, Johnson and Armstrong, 1993).
Components of a good Research Design:
• Define the information needed
• Determine the type of research to be undertaken: exploratory, descriptive, or causal
• Specify the collection instruments and scaling procedures
• Specify the sampling process and sample size
• Develop a plan for data analysis
• Specify budgeting and project scheduling
Characteristic of a good design
a) Has power to detect relationship among variables
b) Appropriate for the research questions
c) Minimizes bias and maximizes the reliability
d) Has smallest errors
e) Yields maximum information and provide an opportunity for considering many different
aspects of a problem

5.3 Population and Sampling Design
5.3.1 Population
The researcher should identify and describe the characteristics of the population involved in the
study. Population refers to the entire group of people, events, or things of interest that the
researcher wishes to investigate. Population forms a basis from which the sample or subjects for
the study is drawn.
5.3.2 Sampling Design and Sample Size
In this section, detailed description of sampling method and the actual sample size should be
provided. Sampling methods may include probability and non-probability techniques.
In non-probability sampling designs, the elements in the population do not have any probabilities
attached to their being chosen as sample subjects. This means that the findings from the study of
the sample cannot be confidently generalized to the population. Typical examples of non-
probability sampling techniques include convenience sampling, and purposive sampling.
To ensure fair representation and generalization of finding to the general population, probability
sampling technique should be used. Typical examples of probability sampling include simple
random sampling, systematic sampling, stratified random sampling and cluster sampling. The
sample size should, therefore, be representative of the general population.
5.4 Data Collection Methods
In this section, the researcher should describe the major methods for collecting data from the
subjects. The major methods for obtaining data in a study may include interviews, questionnaires
and observation techniques. The data collection instruments should be developed and organized
on the basis of the research questions or specific objectives to ensure relevance to the research
problem. A description of the instruments should be given, whether they are researcher
developed or standardized instruments. A description of the nature of instrument items, validity
and reliability, and administration procedures should be provided.

5.5 Research Procedures
A detailed description of the steps taken in the conduct of research should be provided for the
purposes of replicability. The researcher should provide a complete account of the research
process including pilot testing, scheduling of the subjects or participants, distribution and
collection of the instruments and the running of the experiments. Procedures may also include
timing of interviews or questionnaires and instructions given to subjects.
5.6 Data Analysis Methods
The researcher should identify and describe appropriate data analysis methods for the study.
Quantitative approaches in terms of descriptive statistics or inferential statistics should be
described. Descriptive statistics include frequencies, measures of central tendencies (mean,
medium or mode) and measures of dispersion (standard deviation, range or variance). Inferential
statistics involve measurement or relationships and differences between or among the variables.
Inferential statistics include correlation, regression and analysis of variance among others.
Data analysis tools in terms of computer application packages (Excel, SPSS or SAS) should also
be described. Data presentation methods in terms of tables, graphs or charts should also be
described in this section. Qualitative data should be summarized and categorized according to
common themes and presented in frequency distribution tables.
5.7 Chapter Summary
The methodology chapter should end with a summary or synopsis of the main elements
discussed in the section.

LESSON SIX: DATA ANALYSIS AND PRESENTATION OF RESULTS
6.1 Chapter Four: Data Analysis and Presentation of Results
Introduce us to what we expect to find in the chapter. In addition tell us how you have organized
the chapter.
6.2 Analysis of the Response Rate
Tell us how many questionnaires you issues, how many where returned and what is that response
rate (Insert a table also)
6.3 Analysis of the Background Information
This section will enable you to analyze the background information of the questionnaire. i.e. the
gender, level of education, marital status .etc
6.4 Quantitative Analysis
Used to analyze and present results of the closed- ended questions in the questionnaire and you
should organize the section based on your objectives in chapter one.
6.5 Qualitative Analysis
Used to analyze and present results of the open-ended questions in the questionnaire through
capturing the common answers in the open -ended questions based on their commonality through
content analysis. Also organize the section based on your objectives in chapter one.
6.6 Overview
This is generally the longest section of the research project. The objective is to present and
explain the data rather than draw interpretations or conclusions. The findings should be presented
and analyzed on the basis of the research questions, specific objectives or hypotheses. Tables,
charts or graphs should be used to present quantitative data when appropriate. A brief description
in words of what is shown in the table or figure should be provided. A general rule is to prepare
the table or figure and the text, in such a way that they can stand alone in describing the
outcomes of the study

LESSON SEVEN: SUMMARY, CONCLUSIONS AND RECOMMENDATION
7.0 Chapter Five: Summary, Conclusions and Recommendation
This chapter is generally considered as the most critical section of the research project and the
most difficult part to write. The chapter, however, should have a framework that includes the
following:
 Introduction
 Summary
 Discussion
 Conclusions
 Recommendations
7.1 Introduction
The section should start with a brief summary of the structure or organization of the chapter.
Introduce us to the chapter, for example this chapter will present summary of findings, answers
to research questions, conclusions will be drawn from the data analysis performed in this chapter
four. Implications drawn from this study and its impact on policy and professional practice will
be discussed, subsequently. The study will end with recommendations reached.
7.2 Summary
The final chapter of the research project should provide a summary of important elements
including the purpose of the study and research questions or specific objectives, methodology
used and major findings or results. You are supposed to provide a pre-view of the main purpose
(i.e. the general objective or the problem) of the study and the specific objectives, which directed
the study, then provide a summary of findings from chapter four supporting your findings with
statistics from data analysis. Organize this section based on your specific objectives such that
each objective forms a paragraph on its own.

7.3 Discussion
The discussion section should focus on the major findings of the study and should be organized
or structured according to the research questions, specific objectives or hypothesis. The section
should not be a repeat of the study findings and results as presented in chapter 4, instead it
should provide interpretation of the results by comparing them to the findings of previous studies
or theoretical background presented in the literature review.
This section serves to present the specific discussion about each of the research questions as a
first step in addressing the research problem. The research questions first developed in Chapter
one are re-stated and answers provided from chapter four (Data analysis & Presentation of
Results). The answers are discussed by comparing with your literature review in chapter two
reviewed at proposal level.
7.4 Conclusions
In this section, major conclusions drawn from the research findings should be presented.
Conclusions should be drawn about each of the specific objectives based on the answers
provided above for the research questions/based on research findings.
7.5 Recommendations
Research projects should provide recommendations for practice or improvement and for further
studies. In applied research recommendations are often provided for practice or improvement. In
this case the researcher offers suggestions for improvement with justification. Research projects
often pave way for further work. Consequently, the researcher should provide suggestions for
future research work based on the findings and conclusions generated from the study.

LESSON EIGHT: MISCELLENEOUS
8.1 Documentation Styles
To avoid plagiarism in research projects, a researcher is required to acknowledge the sources of
words, facts, or ideas borrowed from other scholars. Most academic disciplines or professional
bodies require special documentation formats or styles in research project reports. Consequently,
the style used should be consistent with the requirements of each discipline. For example, the
American Psychological Association (APA) style is commonly used in social sciences, business
and economics fields; the Institute of Electrical and Electronics Engineers (IEEE) style is used in
electrical engineering and computer science fields; the Chicago style is used in history,
philosophy and humanities; and the MLA style is commonly used as a guide in English and
foreign languages fields.
Most professional publications have abandoned the use of footnotes or endnotes as a method of
referencing within text and have adopted instead the author/year method of documentation. The
author year method provides the reader with names and dates in the text that can be used to
identify complete bibliographic listings in the reference list. One main advantage of the
author/year method is that it offers key documentary information where appropriate within the
text in order to ensure continuity in reading and economic use of the page particularly where
lengthy documentary information is required.
8.2 The APA Style
The American Psychological Association (APA) publication style started way back in 1928 as a
writing style among the psychologist scholars and professionals. Over the years, the APA style
gained acceptance in other scientific and non-scientific fields such as business and economics as
a standard format for writing scholarly papers. Today, it is estimated that thousands of scholarly
journals, magazines, and book publishers in the United States and other countries in the world

require authors to use APA style. APA style uses the author-date method of citation. That is, the
surname of the author and the year of publication are inserted in the text at the appropriate point.
8.2.1 Documentation in Text
Citation of an author’s work in text is used to document work, briefly identify the sources for
readers, and to enable the readers to locate the source of information in the alphabetical reference
list at the end of the paper. The sources of reference chosen should be relevant and current.
i. Work by a Single Author
APA style uses the author-date method of citation; that is the surname of the author and
the year of publication are inserted in the text at the appropriate point. For example:
Human resource management can be defined as the management of activities undertaken
to attract, develop, motivate, and maintain a high performing workforce within the
organization (Harvey, 2001).
Kamau (1998) compared reaction times…………
In a recent study of reaction times, Kamau (1998), described the.. …... Kamau also found
that ………….
Within a paragraph, you need not include the year in subsequent references to a study as
long as the study cannot be confused with other studies cited in the article.
ii. Work by Two or More Authors
When a work has two authors, always cite both names every time the reference occurred
in text.
For example:
According to Bowin and Harvey (2001) human resource management can be defined as
the management of activities undertaken to attract, develop, motivate, and maintain a
high performing workforce within the organization.
When a work has more than two authors and fewer than six authors, cite all the authors

the first time the reference occurs. In subsequent citations, include only the surname of
the first author followed by “et al.” and the year.
For example:
Kamau, Otieno, Patel, Smith, and Wanjiku (1998) found. …[first citations]
Kamau et al. (1998) found. ……………[subsequent citations]
Join the names in a multiple –author citation in running text by the word “and”. In the
reference list join the names by and ampersand “&”.
For example:
Wanjuki and Otieno (1999), demonstrated that ………..… [in text]
Wanjuki, M. & Otieno, J. (1999). Customer satisfaction..[in reference list]
iii. Corporate Authors
The names of corporate authors are usually spelled out each time they appear in a text
citation. The name of some corporate authors are spelled out in the first citation and
abbreviated there after. Corporate authors include organizations, associations or
government agencies.
For example:
First text citation:
(National Institute of Mental Health [NIMH], 2001)
Subsequent text citations:
(NIMH, 2001)
iv. Authors with the Same Surname
If a reference list includes publications by two or more authors with the same surname,
include the author’s initials in all text citations to avoid confusion even if the year of
publication differs.
For example:

S. E. Patel (1996) and G. K. Patel (1990) also found …………
v. Specific Parts of a Source or Quotation of Sources
To cite a specific part of a source, indicate the page or chapter at the appropriate point in
text. Always give a page number for quotations. Note that the word page and chapter are
abbreviated in text citations.
For example:
(Doti and Ruby, 1999, p. 10)
(Wilmarth, 2001, chap. 3)
By:Muathe SMA; PhD (student), MBA, AM1K6 IM
Smith (1999) stated that “The placebo effect disappeared when ….. behaviors were studied in
this manner” ( p. 276).
8.2.2 Reference List
The reference list at the end of the project report or term paper provides the information
necessary to identify and retrieve each source. Researchers should choose references judiciously
and must include only the sources that were used in the preparation of the research project
i. Agreement of Text and Reference List
Reference cited in the text must appear in the reference list; conversely, each entry in the
reference list must be cited in the text. The author must make certain that each source referenced
appears in both places and that the text citation and reference list entry are identical. Failure to do
so can result in an expensive change after the research project report has been bound.
ii. Reference List Format and Order
The reference list format should provide the author’s last name and initials, the year of
publication, the title, the city, and publisher in that sequence. The entries in the reference
list should be arranged in alphabetical order by the surname of the first author.

For example:
Achieng, O. (1998, December 14). Computer groups plan standards.
The New York Times, p. D5.
Booker, C. (1997). Technology and Innovation in the International
Economy. Cheltenham, UK: Edward Elgar Publishing Company .
Cooper, J. & Michie, J. (1997). Technology Innovation and
Competitiveness (ed) Cheltenham, VI/C: Edward Elgar Publishing .
Dessler, G. (2000). Human Resource Management, Upper Saddle River,
NJ: Prentice Hall
Hussey, D. (1997). The Innovation Challenge. New York: John Willey & Sons.
Leenan, B. (2000). Customer Satisfaction Surveys Miss the Mark, [Online]
Available: http://www.findarticles.com
Spinner, M.P. (1990). Elements of Project Management: Plan,
Schedule and control. Englewood Cliff, N.J: Prentice Hall.
Syrett, M. & Lammiman, J. (1998). Managing Live Innovation. Oxford:
Butterworth – Heinemann.
Zahra, S.A., & Ali, A.J . (1997). The Impact of Innovation and
By:Muathe SMA; PhD (student), MBA, AM1K7 IM
Technology in the Global Marketplace. New York: International
Business Press.
8.3 PLAGIARISM IN RESEARCH PROJECT
Plagiarism is the presentation of someone else’s ideas or words as your own. Whether deliberate
or accidental plagiarism is a serious and punishable offense in research projects. Students found
guilty of plagiarism get an E grade in research project or may be disqualified from a
degree/diploma candidacy.

Deliberate or accidental plagiarism occurs when a writer draws words, phrases or passages from
someone else’s work and presenting them verbatim as his/her own work without providing
complete documentation or source citation.
Deliberate plagiarism may include:
• Copying or downloading someone else’s work (a phrase, a sentence or a longer passage) and
passing it off as your own without proper source citation.
• Handing in as your own work, a paper you have bought, had a friend write, or copied from
another student.
• Summarizing, or paraphrasing someone else’s idea without acknowledgement in a source
citation.
Accidental plagiarism may include:
• Forgetting to place quotation marks around another writer’s words.
• Omitting a source citation for someone else’s ideas without acknowledgement in a source
citation.
To avoid plagiarism the researcher should always acknowledge other people’s ideas that are not
common knowledge.

Research Methodology

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Research Methodology

Uploaded by

Copyright:

Available Formats

2014

HCOB 2403:RESEARCH METHODS

Contact Hours Lectures Seminar/Practical Totals

Credits Credits Exam Hours

 Demonstrate knowledge on the process of conducting research and

 Selecting A Research Topic

 Formulating The Research Problem

Research Methods Page 2

O.M Mugenda and A.G Research Methods : Acts Press

M. Saunders, P. Lewis and Research Methods for Dorling Kindersley Pvt.

Kate L. Turabian A Manual for Writers of The University of

Research Methods Page 3

Research Methods Page 4

A. COURSEWORK AND PROJECT PROPOSAL

(1) Assignments and/or CAT……………… 20%

(2) Research Proposal a) Proposal document 30%

b) Presentation & defense 20%.

(3)Final Exam ………………………………………… 30%

B. FIELDWORK AND FINAL PROJECT

(1)Fieldwork and Final Research Project Report..………………………100%

Research Methods Page 5

1.1 What is research?

 There are many ways of defining “research”

 To research is to carry out a diligent inquiry or a critical examination of a given

to newly discovered facts

 Research is a systematic, controlled, empirical, and critical investigation of hypothetical

prepositions about the presumed relations among natural phenomena

 Research is the process of arriving at dependable solutions through a systematic

collection, analysis and interpretation of data

 Research is the careful and systematic inquiry into or examination of a field of

knowledge in order to establish facts and principles.

carefully planned, implemented, disseminated, and consumed.

1.1 Purposes of research

discovery of new facts, their correct interpretation and practical application.

 Secondly, is to describe a phenomenon. Accurate identification of any event involves

 Thirdly, is to enable prediction. This is the ability to estimate phenomenon. We

sometimes use a set of variables to predict a given variable.

 The fourth purpose of research is to enable control. In scientific research control is

experiments are designed to achieve this objective.

Research Methods Page 6

involves accurate observation and measurement of a given phenomenon.

 The sixth purpose of research is to enable theory development. Theory development

involves formulating concepts, laws and generalization about a given phenomenon

1.3 Distinguishing characteristics of research

 Research is empirical. It deals with data, which is tested scientifically.

 Research is self-correcting. The results of research are open to public scrutiny.

1.4 Research and Knowledge

sources of knowledge, namely: -

microfinance and improving it.

Research Methods Page 7

 Dogma and tradition

1.5 Areas of research in microfinance

 Opinions and attitudes

 Needs of the people

 Feasibility of proposed microfinance products and/or activities

 Identifying relevant approaches and models

 Evaluation of ongoing programs, current products, policies, procedures, approaches, etc.

human behavior and how certain events affect human behavior.

1.6 Quality Requirements of Research Projects

Whether a student is seeking to complete a diploma, degree at an undergraduate level or

as conformance to requirements or fitness for purpose. Degree/Diploma project demonstrates the

 Make contribution to the knowledge in the discipline,