RESEARCH METHODS LECTURE NOTES

COURSE OBJECTIVES
By the end of the module students should be able to;
a. Describe basic concepts in research, monitoring and evaluation
b. Outline steps in designing data collection tools for projects
c. Collect and analyze data using appropriate analytical tools
d. Develop and carry out research projects

A. INTRODUCTION

Meaning of Research
 In simple terms: - It’s the process of finding out information about something or an issue/
an activity designed to provide answers to questions about simple day-to-day life
activities/ It’s a way of gathering evidence
 In scientific terms, research is a mechanism of collecting, classifying, analyzing
discussing summarizing and drawing valid conclusions about a population based on
information contained in a sample
 Research is a systematic and objective search for, and analysis of, information relevant to
the identification and solution of a problem or to the discovery of a principle
 Systematic approach: Involves careful planning through all stages of research
i.e clear and concise statement of the problem, required information,
analytical techniques
 Objectivity: Bringing new and reliable information for better decisions.
Hence, scientific methods are crossly accepted.
 Analysis: Data must be converted into information before it becomes useful in
decision making
Importance of Research
 Understanding a phenomenon/issue
 To gain knowledge about phenomena that may or may not have applications in
the near future
 It helps researchers to apply techniques learnt from other disciplines to solve
problems (Applied Research), therefore it helps in formulating models…)
 Research is geared at answering questions of immediate importance and
contributes to theory testing processes
 To come up with solutions to address challenges in the society or any profession.
 To develop new techniques and procedures that form the body of research
methodology
 It also assists us to approach our research in a manner that incorporates reality by
coming up with conclusions and recommendations that are implementable
e.g. a particular product may not be selling well and the manager might want to find the reason
for this in order to take corrective action.
Research Ethics
There are some ethical issues involved in conducting reliable research.
What are Research Ethics?
 Ethics in research refer to a code of conduct or expected norm of behaviour while conducting
research.
 Following research ethics and norms helps a researcher to pursue research objective rather
than self-interests.
 Ethical conduct should be reflected in the entire research team including the researcher,
participants providing the data, analysts who provide the results etc.
Ethics in data Collection
Ethics in data collection pertains to those who sponsor the research, those who collect the data
and those who provide the information.
I. Sponsor
The sponsor should respect the confidentiality of information obtained by the researcher.
S/he should not ask for disclosure of individual sources of information. The sponsor can
only request to see questionnaires for monitoring purposes
II. Researchers
 Have informed consent from participants
 They should know the risks, objectives and agreed voluntarily to participate
 Safeguard social and physical environment of participants
 Explain reasons for the study
 Treat information given with strict confidentiality
 Personal or intrusive information should not be solicited or with strong reasons if it is
needed by the project,
 No-participant observers should not be as non-intrusive as possible. If they intrude, the
quality of data may be affected
 Never expose subjects/ respondents to situations that will physically or mentally harm
them,
 Avoid distortions and misinterpretations of collected data.
 When children or other vulnerable groups are involved you need clearance & consent
from guardians
 Always get authorization from relevant authorities
 Do research to the benefit of society/community i.e. academic community &
development community •
 Safeguard against disseminating results that will be detrimental to society.
 Never claim knowledge of something you did not generate (lying/ failing to acknowledge
source)
III. Respondents
Ethical behaviour of respondents hinges on:
  Full cooperation once offer to participate is accepted,
 Truthfulness and honesty in responses.

Types of Research and Their Processes

There are two broad types of research:
1. Basic or Fundamental or Pure Research which seeks to extend the boundaries of
knowledge in a given area with no necessary immediate application to existing problems.
2. Applied or Decisional Research which attempts to use existing knowledge as an aid to
the solution of some given problem or set of problems.
Research Design
It’s the specification of procedures for collecting, analyzing and presenting data. It should
respond to expected value of information and the cost of obtaining the information.
Steps in the research design process
Step 1: Define the research problem
Step 2: Generate hypotheses
Step 3: Select type(s) of study appropriate to the problem
Step 4: Select the data collection methods
Step 5: Select the measurement technique
Step 6: Select the sample (Sampling Design)
Step 7: Select the analytical approach (techniques)
Step 8: Specify the time and financial cost (work plan and budget)
Step 9: Prepare the research proposal
Step 1. Defining a problem
• A problem may be defined as any situation where a gap exists between the actual state or
situation and the desired ideal state.
• Research problem definition involves the following:
A. Describing the Statement of the Problem;
B. Providing objectives of the study;
C. Specifying the type of information needed; and
D. Deciding on the title.
 a. Description of the statement of the problem
• Most critical part of research process.
 Unless the problem is properly defined, information collected is unlikely
to have any value
• The basic goal is to ensure that the description of the problem is accurate and reflects the
appropriate area of concern for research.
• This involves the following:
• Identifying broad problem area; and
• Defining the Statement of the Problem.
a. Identification of broad problem area
• The first thing is to find a problem which is also important to other people e.g. potential
donors, supervisors, collaborators.
• To do this:
i. Define domain (field) e.g., Agric Econ, Nutrition, Environment, ABM;
ii. Identify broad problem area that fits into existing strategies, e.g., high poverty
levels, poor nutrition, low yields, natural resource degradation, etc.
iii. Must be familiar with general policy documents and frameworks, e.g. MGDS II,
ASWAp, MDGs, sector policies & strategies, general literature of the proosed
area of study
b. Definition of Statement of the Problem
A Statement of a Problem is a clear, precise (accurate) and succinct (brief)
statement of the question or issue that has to be investigated with the goal of
finding an answer or a solution.
• To come up with the Statement:
i. Specify the needs, e.g., reduce poverty, eradicate hunger, safeguard environment,
improve nutrition, etc;
ii. Identify constraints, e.g., low rainfall, poor & degraded soils, etc;
iii. Gather information to understand and be able to narrow down broad problem to
Statement of the Problem
 Literature review and exploratory/reconnaissance survey
An example of a research problem statement
 • Malawi, like most Sub-Saharan African countries, presents a case of policy dilemma in
sustainable forest management. With its increasing population and the resultant
contraction of per capita land area, coupled with the ever increasing fuel wood demand,
the challenge is to sustainably manage the forests without alienating the majority of local
communities whose livelihoods heavily depend on the forests. There is therefore need to
fully understand the forest-reliant people if the goal of sustainable forest management is
to be achieved. This study contributes to filling that information gap by assessing the role
and determinants of forest reliance on livelihoods of rural households surrounding
Chimaliro and Liwonde forest reserves in Malawi.” (Chilongo, 2014: 1-2)
B. Objectives of the research
• Objectives indicate what you intend to achieve through your research. They are normally
categorized into:
A. Underlying (Main) Objective – overall purpose or aim of the study; and
B. Specific Objectives – functional statements of the tasks to be addressed in order
come up with solutions.
In other words, specific objectives state how the main objectives will be achieved
Characteristics of research objectives
Objectives should be
• Simple and easy to understand by most people in the discipline;
• Clearly understood by the researcher;
• Predictable from the title;
• Logical ( make scientific and socioeconomic sense);
• Based on real situations not imaginations (unless intended for discoveries);
Achievable within the study timeframe using the outlined resources
• Consequently, objectives should be SMART:
• Specific – qualify exactly what has to be achieved, where and by who (beneficiary)
• Measurable – quantify the achievement (where possible).
• Attributable – strongly linked to expected output.
• Realistic – can be reliably, cost-effectively and timely achieved.
• Time bound – state when the achievement must be reached.
C .Specifying the type of information needed
• Research problem definition also involves specifying the types of information that are
needed to help solve the management problem.
 – Leads to choice of the type of study appropriate for the problem [to be discussed
in detail in step 3 and Topic 6]
• Whether we need primary, secondary data or both
• Whether we need exploratory, descriptive study or both
D. Title of the Research Project
• Titles matter. A good proposal title sells the proposal. A memorable or arresting title will
draw attention to your proposal.
• Probably, the title will be read more than any other section of the proposal, may be
reprinted in bibliographies and subject indices (databases). Titles are an important source
of information.
A good title
• Contains as few words as possible (25 words or fewer).
• Describes the contents of the proposal accurately.
• Avoids abbreviations/acronyms, parentheses, formulas and jargon.
• Is understood by the general reader (not too technical).
• Contains key words (for the benefit of information retrieval).
• Is catchy and conveys the urgency, importance or benefits of the project
Two-Part Titles: The Colon Trick
• The colon trick may help write titles that are both catchy (first part before the colon) and
scientific (second part after the colon):
– 1st Part: short, snappy, easy to read;
– 2nd Part: serious and informative.
Example 1
Old title
• Evaluation of pitting technology for the renovation, re-vegetation and increased
productivity of eroded grazing land
Improved titles:
• Pitting and ridging: can a new technology save poor soils?
• Pitting and ridging: a new technology to increase the productivity of poor soils
• Example 2
Old title
• Transmission of African cassava mosaic virus (ACMV) by Bemisia hancocki (whiteflies)
Improved titles
• Protecting a poor people’s crop: the biology and management of the white flies that
transmit the African cassava virus.
• Increasing cassava yields: the biology and management of the white flies that transmit the
African cassava virus
Step 2. Generating hypothesis
• A hypothesis is a conjectural (speculative) statement of the relation between two or more
variables.
– It is an explicit proposition, supposition, speculative or provisional explanation
derived from personal prejudices, opinion, theories and notions based on slight
evidence and experience.
– It reflects what you think is true based on available evidence but still needs to be
proved.
Research sets out to prove or disprove the validity of the hypotheses
• There are two characteristics which all hypotheses must have:
i. they must be statements of the relationship between variables; and
ii. the variables musts be measurable.
 We test relationships and not the variables. Hypotheses specify how the variables are
related and that these are measurable or potentially measurable.
 Hypotheses must be formulated in such a way that they are non-trivial, testable and
capable of being refuted.
Example 1: Consider the following alternate/research hypothesis:
Beef consumption increases as real disposable income increases.
• The hypothesis states the relationship between one variable, beef consumption, and
another variable, real disposable income, and both variables are potentially measurable.
 Criteria are satisfied and the above statement qualifies as a hypothesis which can be
tested empirically.
 We may state the hypothesis in the null-form, i.e., present the null hypothesis for
purposes of statistical testing.
 The null hypothesis presents the supposition in such a way you would expect it to
be disproved. It posits that there has been no change or difference.
 There is no relationship between beef consumption and the level of real
disposable income
• Example 2: Consider the following null hypothesis:
Advantages of stating hypotheses
1. Hypotheses help the researcher concentrate on gathering relevant data, data that will
enable testing of hypotheses.
2. By stating hypotheses, our notions or explanations for events become explicit .
3. A Statement of the Problem cannot be solved unless it is reduced to hypothesis form; the
statement is too broad and not directly testable.
Research Questions
• Research questions are generally used for exploratory research, when researchers have
less past knowledge to draw predictions about possible relationships between variables.
• Otherwise, a research question should retain most of the main characteristics of a
hypothesis such as measurable, specific, testable, etc.
Research Questions: Examples
1. Is there a relationship between beef consumption and disposable income?
2. Do multiple sources of livelihoods reduce forest degradation?
3. Do university graduates earn more than non-graduates?
Research Questions: How to Phrase Them?
Note that good research questions should be phrased in such that the answer is Yes or No.
From the previous example:
1. “Is there a relationship between beef consumption and disposable income?” is
better than “What is the relationship between beef consumption and disposable
income?”
However, it is not necessarily wrong to have “non-Yes/No” research questions but where
possible, they should be avoided.
Research Questions vs Hypotheses
• Some people use research questions instead of hypothesis. Others use both hypotheses
and research questions.
• Currently there is no consensus on whether to use research questions in place of
hypotheses and vice versa or whether they can be used together.
 • For this course, I recommend that you do not use them together. Choose one of them at a
time.
Step 3: Selecting Type(s) of Study Appropriate to the Problem
• Research can be carried out on one of the following three levels:
a. Exploratory;
b. Descriptive; and
c. Causal.
a. Exploratory research
• The research can take the form of
– literature search/review,
– informal personal interviews and
– focus group discussions
– Reconnaissance survey/visit
b. Descriptive research
• Concerned with description of characteristics of units of the measurement, e.g.,
i. The households (household survey). The research describes e.g.
– The socio-economic characteristics of the household e.g.
• gender, age, education level, status of household head.
• Household composition.
• Household size.
• Household income
ii. Farming system. In this case, it describes e.g.,
• Land holding characteristics e.g. land tenure, land holding size, land
taxes.
• Cropping patterns (area allocated to different crops)
• Livestock kept
• Input levels
• Production levels
• Yields
C. Causal research
• Causal research deals with the why questions. Why a change in one variable brings about
a change in another.
• If we can understand the causal effects we observe, our ability to predict and control such
events is increased.
• Quantitative techniques such as regression analysis are normally used.
• Most studies combine elements of all the three types of research
Step 4: Selecting the Data Collection Method(s)
• There are three basic data collection approaches:
– Secondary data;
– Survey/primary data; and
– Experimental data.
• Determine whether secondary data, a survey, experimentation or a combination of more
approaches will produce the required data and choose the form, of the selected method to
use (major data collection methods are discussed later).
Step 5: Selecting the Measurement Techniques (data collection tools)
• After selecting the data collection approach, the researcher must develop a measurement
instrument.
• Measurement techniques used include:
– Questionnaires;
– Checklists;
– Attitude scales (e.g. rating scale/ranking);
– Observation;
– Depth interviews; and
– Visualization techniques (e.g., transects, seasonal calendars, flows diagramm,
decision tree, Venn diagramme).
Step 6: Selecting the Sample
• Most social studies involve a sample or subgroups of the total population relevant to the
problem, rather than a census of the entire group. Determine who and how many
respondents or objects to measure.
The major considerations in sampling are described in detail later
Step 7: Selecting the Method(s) of Analysis
• Analytical techniques should be selected prior to collecting the data.
• Data analysis involves converting a series of recorded observations/data into information
that can be used by the decision-maker
– Descriptive analysis, e.g., means, frequencies, correlations and making inferences
about relationships.
 – Quantitative analysis – models e.g., regression models
Step 8: Estimate Time and Financial Requirements
Time requirement (work plan) - time period needed to complete the project. In the work plan,
you
(a) specify the activities and when those activities will be carried out normally in a
chart form
(b) specify the Person days required for the different activities
Tips on preparing good proposal budget
 Proposal budget is one of the most important sections; many potential sponsors
only look at the summary, the objectives and the budget and may base their
accept-or –reject decision on only those sections.
 Use a consistent budget format in all proposals, except for those where the donor
has a preferred format.
 Prepare budget guidelines to ensure that everyone in your organization is
preparing budgets under the same financial assumptions, and that the same costs
are offered to donors in all proposals.
 Budgets should be clear, transparent and easy to read.
 Anyone should pick up your budget and understand it without having you to be
there to explain your costs assumptions

2CLASSIFICATION OF RESEARCH
Research is generally classified into 3 types:

 Experimental Research
Biology, chemistry etc lab experiments

 Quasi –Experimental Researc

Includes laboratory research and field research. e.g. research on crop hybrids

 Observational Research
Observation of socio-economic problems through questionnaires and interviews etc

Qualitative And Quantitative Research

Research methods are split broadly into quantitative and qualitative methods .
QUANTITATIVE RESEARCH METHODOLOGIES

Quantitative research
– Research strategy based on measurement of quantity or amount. – It is used to quantify the
problem by way of generating numerical data or data that can be transformed into useable
statistics. – Used to quantify attitudes, opinions, behaviours, and other variables. – Emphasizes
quantification in the collection and analysis of data. – E.g. Survey using structured
questionnaires, secondary quantitative data collection.
There are four main types of quantitative research designs: descriptive, correlational, quasi-
experimental and experimental
EXPERIMENTAL RESEARCH
 Is one of the most powerful research methodologies that researchers can use.
 Experiments are the best way to establish cause and effect relationships.

UNIQUENESS OF EXPERIMENTAL RESEARCH

Experimental research is unique in two respects:
 It is the only type of research that directly attempts to influence a particular variable.
 It is the best type for testing hypotheses about cause and effect relationships

In experimental studies, researches look at the effect(s) of at least one in dependent variable on
one hand or more dependent variables.
An independent variable is also known as the Experimental or treatment variable (e.g. fertiliser).
The dependent variable is also known as the Criterion or Outcome variable.
The major characteristic of experimental research distinguishing it from all other types of
research is that researchers manipulate the independent variable e.g. change fertilizer dose to see
or observe changes in yield of a crop.
ESSENTIAL CHARACTERISTICS OF EXPERIMENTAL RESEARCH
The basic idea underlying all experimental research is quite simple: try something and
systematically observe what happens.
Comparison of groups
 An experiment involves two groups of subjects:
- An experimental group
- A control or comparison group
 It is however possible to conduct an experiment with only one group or three or more groups.
 The experimental group receives treatment of some sort .
 The control group receives no treatment or the comparison group receives a different
treatment.
 The control or comparison group is very crucial in experiments because it enables the
researcher to determine whether the treatment has had an effect or whether one treatment is
more effective than another.
 A pure control historically receives no treatment at all (hence comparison groups since
sometimes they receive treatment).

Manipulation of the independent variable

 In experimental research, the researcher actively manipulates the independent variable e.g.
feeding rations
 However, certain independent variables cannot be manipulated such a gender, ethnicity, age,
etc. e.g. effect of somebody’s age on memory or formation of certain vitamins in the body.
 Independent variables in an experiment may be established in several ways:
 -One form of variable against another. 20:20:0 vs. Urea
 -Presence vs. absence of a particular form.
 -Varying degrees or doses of same form.

Randomisation
Experimental research is characterised by random selection and assignment
 Random assignment means that every individual participating in the experiment has an equal
chance of being assigned to any of the experimental or control conditions being compared.
 Random selection on the other hand means that every member of a population has an equal
chance of being selected to be a member of the sample.

Control of Extraneous variables

Researchers in Experimental Research exercise for more control than in most forms of research.
.
You want to control extraneous variables because you want to be sure of the causes of the
observable effects on your variable. The idea is to ensure that variables are as equivalent as
possible on all variables except the ones being studied. Researchers can minimise or eliminate
threats due to subject characteristics in the following ways:
Randomisation
If enough subjects can be randomly assigned to the various groups involved in an experiment,
researchers can assume that the groups are equivalent.
Hold certain variables constant
Holding other variables constant eliminates the possible effects of a variable by removing it from
the study e.g. if gender influence an experiment, the use only people or elements with one
gender.This however reduces the generalizability of the results.
Build the variable into the designs
Involves building variables into the study to assess their effects e.g. using both males and
females and later analyse the effects of both gender and method outcomes.
Matching
Pairs of subjects can be matched on certain variables of interest e.g. if age effect outcomes from
a certain experiment, you use elements of the same age.
Use subjects as their own control
You assess performance of both (or all) treatments e.g. testing somebody’s behaviour before and
after learning something.
QUALITATIVE RESEARCH

Qualitative research refers to research studies that investigate the quality of relationships
activities situation or materials. It has more emphasis on holistic description (ie describing in
detail all of what goes on in a particular activity or situation rather than on comparing the effects
of a particular treatment)
Qualitative research strives to define human behavior and explain the reasons behind
that behavior. Often used in commercial areas such as market research, the goal of
qualitative research is to provide answers as to why and how people come to make
certain decisions. There are several different approaches to undertaking qualitative
research.

GENERAL CHARACTERISTICS OF QUALITATIVE RESEARCH

According to Bogdan and Biblen qualitative research has got five features:
1. The Natural setting is the direct source of data and the researcher is the key instruments
Qualitative researchers go directly to the particular setting of interest to observe and collect
data. They believe that activities can be best understood in the setting in which they occur
and believe that human behaviour is affected by the environment
Qualitative data are collected in form of words or pictures rather than numbers. Kinds of data
collected include interview transcripts, field notes, photographs, diaries, video tapes, audio
tapes, personal comments, official records or anything that can convey words or actions of
the people. No attempts are made to reduce data into numerical symbols. Joke, gestures,
decorations are all noted by qualitative researchers. To qualitative researchers, no data is
trivial or unworthy. Qualitative Researchers are concerned with process as well as product
and are interested in how things occur
 They are this likely to observe the following
 How people interact to each other
 How certain questions are answered
 Meanings given to certain words
 How beliefs and attitudes are translated into actions

2. Qualitative researchers tend to analyse their data inductively

They do not to formulate hypothesis before hand, they like to play as it goes. They prefer to
collect data before they decide what are the important questions to consider.
How people makes sense out of their lives is a major concern to a qualitative researcher.
They Want to know what participants in the study are thinking and why they think in that
way.
Assumptions, motives, reasons, goals values are all of interest and a focus of interest. They
Usually show their findings to participants in order to ascertain accuracy of interpretation.

STEPS IN QUALITATIVE RESEARCH

Steps in conducting qualitative research are not as distinct as in quantitative research
The steps often overlap or run concurrently. These steps are highlighted below.
Identification of phenomenon to be studied
Involves identifying phenomena to be studied ie phenomena of interest to the research. It is also
known as identification of foreshadowed problems
These fore shadowed problems can be reformulated several times during course of study
Identification of participants in the study
These will constitute the sample of study. They are essentially individuals/subject to be studied.
This process is also known as Purposive Sampling. Random sampling is not feasible.
Generation of hypotheses
Hypotheses are not posed at the beginning of study but emerge from the study progresses. They
can be changed or modified. New hypotheses can also be formulated during the study.
Data Collection
These is no treatment in qualitative research nor is there manipulation of subjects. Participants
are not divided into groups that are subjected to different treatments
Data are not collected at the end of study but is on-going with the study
Data Analysis
Involves synthesising information collected during the study into a coherent description of what
has been discovered or observed. It relies heavily on description although certain statistics can be
used if they help illuminate or explain certain phenomena. The statistics are used in a descriptive
rather than inferential manner.

Interpretation and conclusions

Are made continuously throughout the study
APPROACHES TO QUALITATIVE RESEARCH

BIOGRAPHY
A biographical study is the study of a single individual and his or her experience as told by the
researcher or found in docs or the archives.
Examples of biographers include:

Biography
Biographies are life stories written by individuals themselves

Autobiography
An autobiography is a life story written by the individual himself/ herself.

Life Stories
Life stories are a combination of biographies and autobiography.

Oral Histories
Oral histories are stories in which a researcher gathers personal recollections from a variety of
individuals.
CASE STUDIES
A case involves the study of just one individual, programme or object, eg a school village or an
event. For example, if some people learn languages quickly, their behaviours and attitudes could
be studied to explore noticeable patterns in their behaviours or regularities in their behaviour.
HISTORICAL RESEARCH
Def: Historical research is the systematic collection and evaluation of data to describe, explain
and understand actions or events that occurred in the past
 It is unique because it only focuses on the past
 It examines documents of the past, interviewing people who lived during that time.
 It aims at reconstructing the past and explain why certain things happened

Purposes of Historical Research

 To make people aware of what happened in the past so that they learn from it.
 To see how things were done in the past to see if the they might be applicable to present day
problems and concerns,
 To assist in prediction eg in weather forecasting
 To test hypotheses concerning relationships and trends,
 To understand the present more fully.

ETHNOGRAPHIC RESEARCH
Is the most complex type of research because it deals with humans. It uses a variety of
approaches. It emphasizes on documenting or portraying the everyday experiences of
individuals.
Key tools used in ethnographic research include;
 In-depth interviewing,
 Continual and on-going observations of a situation

Ethnographic Concepts
These are concepts that ethnographers follow as they go about their work. These are as follows;

Culture
It is the sum of a social group’s observable patterns of behaviour, customs and ways of life.
A culture comprises ideas, beliefs and knowledge that characterises a particular group of people.

A holistic Approach
Ethnographers try to describe as much as they can about the culture of a group. Developing a
holistic perspective demands that the ethnographer spend a great deal of time out in the field
gathering data, only then can he/she develop a picture of the social or cultural whole of what is
being studied

Contextualisation
Contextualisation involves placing what was seen and heard into a larger perspective.

Emic perspective
An emic perspective is an insiders’ perspective of reality. It helps in understanding and
accurately describing behaviours and situations.
Member checking
Aims at validating what the ethnographer has written. Participants review what the researcher
has written.

Non-judgemental orientation
This aims at preventing researchers from making judgements about unfamiliar practices,
It helps to guard against biases.
RESEARCH BY PRACTITIONERS

ACTION RESEARCH
Action research is research conducted by one or more individuals or groups for the purpose of solving a
problem or obtaining information in order to inform local practice.

BASIC ASSUMPTIONS UNDERLYING ACTION RESEARCH

 Those doing action research assume that those that are involved are informed individuals who are
capable of identifying problems that need to be solved.
 Those involved are interested in improving their performance and continually reflect in their
performance.
 Those carrying out research have authority to undertake necessary procedures and implement
recommendations.

TYPES OF ACTION RESEARCH

Mills defines two types of action research

(a) PRACTICAL ACTION RESEARCH

 Is intended at addressing a specific problem in a community or social grouping,
 Aims at improving practice in the short term,
 To be effective, it has to result into an action plan that will be further evaluated.

(b) PARTICIPATORY ACTION RESEARCH

 It has two additional purposes as compared to practical action research
-To empower individuals or groups
-To bring about social change.
 All stakeholders involved in participatory action research act as equal partners
 It involves active participation at several levels such as:
- Data collection and analysis.
- Interpretation of data
- Implementation of resulting actions
 It is also known as Collaborative Research

STEPS IN ACTION RESEARCH

1. Identifying the research question
2. Gathering the necessary information
3. Analysing and interpreting the information
4. Developing an action plan.
Sampling and Sample Size Estimation

Sampling
 Sampling is a process of selecting a representative number of elements from a population.
 Sampling errors will always occur when a sample (and not a population) is used.
 Proper and accurate sampling therefore helps us to draw or establish closer relationships
between a sample and the population (through a sample statistic or population
parameter)
Basic Elements of Sampling

Population = entire group of people, or things of interest that researcher wishes to investigate.
◦ e.g., population of Lilongwe district comprises of all households in Lilongwe. Or
AH25 class comprises of 31 students.
Element = a single member of the population.
◦ e.g., if AH25 class has 31 students, each student is an element
Sample = a subset of the population, i.e., as a finite part of a statistical population whose
properties are used to make estimates about the population
◦ e.g., if 20 students are randomly selected from 31 students in AH25 class, the 20
students form the sample.
Sampling unit = an element (or set of elements) that is available for selection at some stage of
the
sampling process, i.e., the unit of sampling
◦ e.g., if you wanted to select sample class, EPAs & sample households, the EPA,
class and household comprise the sampling units
Sampling frame = list of elements (population members) from which you draw your sample.
◦ e.g. List of EPAs, Sections or households
Parameters = characteristics of the population
◦ e.g., population mean, SD & variance
Statistics = characteristics of the sample
◦ e.g., sample mean, SD & variance
Sampling error The difference between the results obtained from the survey sample and those

that would have been obtained had the entire population been surveyed (a census).
Size of sampling error varies both with the size of the sample and with the percentages giving a
particular response
Why get a sample?
 Financial limitations,
 Logistical and geographical limitations,

Basic Requirements of a Sample

 Representativeness
 Adequate size

It is important, therefore, to get a proper sample size or a statistically adequate sample.

Types of Sampling
There are two types of sampling: (i) probability sampling and (ii) nonprobability sampling.

probability sampling
In the case of probability sampling, the probability or chance of every unit in the population
being included in the sample is known due to randomization involved in the process. It is thus a
method of sampling that utilizes some form of random selection. Some methods of probability
sampling are as follows:
a) simple random sampling
It is a method of selecting units out of a population where each element (item or person) has an
equal chance of being selected.
If somebody wanted to select n units from population N, each unit will have 1/N chance of being
selected.
Certain computer software can also help in randomly selecting units out of a population such as
SPSS or GENSTAT or some sophisticated calculators can generate random numbers.
Steps:
1. Obtain a complete sampling frame
2. Assign each case a unique number starting from one.
3. Decide on the required sample size.
4. Select sample in form of raffle draw or using Ms excel

b) Systematic Random Sampling

The first unit is selected on a random basis and then additional sampling units are selected at an
evenly spaced interval until all desired units are selected.
Steps:
1. Obtain a sampling frame
2. Determine the population size (e.g. 200)
 3. Determine the required sample size (e.g. 20)
4. Calculate the sampling fraction – divide the population size by the sample size =
200/20 = 10.
5. Randomly select the starting point by selecting any number between 1 – 20 , e.g.
select 5.
6. In this case the starting number case number 5.
7. Use the sampling fraction to select every n th case. With a sampling fraction of 10,
select every 10th case and obtain 20 cases.

c) Stratified random sampling also called proportional or quota random sampling,

 Involves dividing the population into mutually exclusive and mutually exhaustive
subgroups/strata and then taking a simple random sample in each subgroup/strata.
 Subgroups can be based on different indicators like sex, age group, religion or
geographical regions.
 However, it is to be noted that stratification does not mean the absence of randomness.
 Stratification ensures that special groups are represented in a sample of ethnic groups,
religions, child headed households etc.
When do we use Stratified Sampling Methods?
 When a population has relatively large variability between strata.
 If not used, large groups will have more samples than small groups (districts, regions, tribes)
The results are later weighted to the actual proportion.
Steps:
1. Select the stratifying variable e.g. gender
2. Divide the sampling frame into separate lists – one for each category of the
stratifying variable e.g. males and females.>> Male is a stratum and female is a
stratum
3. Draw a SRS or systematic sample of each list.
Proportional Probability Sampling (PPS)
Is also known as Proportional Sampling. It takes into consideration size of each stratum.
PPS takes out imbalances of sample size in stratified sampling since you use elements
proportional to the size of the strata. It helps to Improve the representativeness of the sample.
Equal allocation
 Same of number of elements are sampled from each stratum, that is, sample size, is given
by:
nh = n/L
- Where n is the desired (overall) sample size
- L is the number strata (total number of strata you have)
  Example: If you want a sample (n) = 300 farmers from an EPA with 5 villages. Therefore
from each village you will select:
nh = n/L
= 300/5
= 60 farmers will be selected from each village.
Proportional allocation
 In this method, the sampling fraction nh/Nh is specified to be the same for each stratum.
 This implies that the overall sampling fraction n/N is the fraction taken from each
stratum.
 Formula: The number of elements nh taken from each stratum is given by nh = Nh*n/N

Example: Consider a population of 255 EPAs, you want to draw a stratified random
sample of 51 EPAs using proportional allocation. If stratum 1 (has) = 44 EPA’s, 2= 116
EPA’s, 3= 48 EPA’s, and 4= 47 EPA’s. Then from each stratum you would sample the
following EPA’s:
• N = 255, required sample size (n) = 51. Then overall sampling fraction is 51/255.
From each stratum:
Stratum # of EPAs
1 44 > n1 = 44*51/255 = 9
2 116 > n2 = 116*51/255 = 23
3 48 > n3 = 48*51/255 = 10
4 47 > n4 = 47*51/255 = 9____
51____

d) Cluster sampling
Signifies that instead of selecting individual units from the population, entire group or clusters
are selected at random.
In cluster sampling, first we divide the population into clusters (usually along geographic
boundaries).
• Then we randomly select some clusters from all clusters formed to measure all units within
sampled clusters in the end. •
Steps on how to select a cluster sample?
 Step 1: List all the sections in an EPA, and draw a random sample of section from this
list.
Step 2: From all the selected Sections, list all the farmers/households, then select a
sample of farmers/households.

NON-PROBABILITY SAMPLING

Non-probability sampling does not involve the process of random selection, that is, in the case
on non-probability sampling, the probability of selection of each sampling unit is not known.
There is no rational way to prove/know whether the selected sample is representative of the
population.
In applied social research due to constraints such as time and cost and objectives of the research
study there are circumstances when it is not feasible to adopt a random process of selection and
in those circumstances usually nonprobabilistic sampling is adopted.
Non-probability sampling methods
a) Accidental or Convenience Sampling
as the name suggests, sampling units are selected out of convenience, for
example, in clinical practice, researchers are forced to use clients who are
available as samples, as they do not have many options.
 Are samples that are taken without plan among a set of units that are readily
available.But, they are not random samples, and usually contain important information.
 Though the sampling appears to be random, the final sample is not representative of the
entire population.
 Such samples may include a larger proportion of people possessing certain
characteristics, than what is there in the population at large.
 Results from such samples cannot be considered to be accurate.
b) Purposive Sampling
As the name suggests, is done with a purpose, which means that selection of sampling units is
purposive in nature. Purposive sampling can be very useful for situations where you need to
reach a targeted sample quickly and where a random process of selection or proportionality is not
the primary concern.
These samples are not based on randomness.
They are based on ones’ judgment that the sample will give them the information they are
interested in (or have a better understanding of the problem they are examining)
Such study will be more qualitative than quantitative.

c) Quota Sampling, .
 Shares some characteristics with stratified random samples, but they are non-
probabilistic.
 They include various groups in the same proportions as in the general population.
 The groups are defined based on a certain criteria, such as, sex, age, income levels,
ethnicity, etc.
  Quota samples reflect the characteristic of the population, but they are not probability
samples
d) Expert Sampling
 Involves selecting a sample of persons, who are known to have demonstrable experience
and expertise in a particular area of study interest.

 Researchers resort to expert sampling because it serves as the best way to elicit the views
of persons who have specific expertise in the study area.

 Expert sampling, in some cases, may also be used to provide evidence for the validity of
another sampling approach chosen for the study.

e) Snowball sampling
 generally used in the case of explorative research study/design, where researchers
do not have much lead information.

 It starts by identifying respondents who meet the criteria for selection/inclusion in

the study and can give lead for another set of respondents/information to move
further in the study

 Snowball sampling is especially useful when you are trying to reach populations
that are inaccessible or difficult to find, for example, in the case of identifying
injecting drug users

ERRORS IN SAMPLING
Sampling Error: It is defined as the differences between the sample and the population, which
occurs solely due to the nature or process in which particular units have been selected.

There are two basic causes for sampling error:

The first is chance, that is, due to chance some unusual/variant units, which exist in every
population, get selected as there is always a possibility of such selection. Researchers can avoid
this error by increasing sample size, which would minimize the probability of selection of
unusual/variant units. •
The second cause of sampling error is sampling bias, that is, the tendency to favour the selection
of units that have particular characteristics.
II. Non-sampling error
Defined as an error that results solely from the manner in which the observations are made and
the reason could be researchers’ fault in designing questionnaires, interviewers’ negligence in
asking questions, or even analysts’ negligence in analysing data.
• Non-sampling error may be due to human error, that is, error made by the interviewer, if he is
not able to communicate the objective of the study or he is not able to cull out the response from
respondents or it could be due to fault in the research tool/instrument.. •
The simplest example of non-sampling error is inaccurate measurements due to poor procedures
and poor measurement tools
SAMPLING BIAS
General precautions to be followed in order to prevent sampling bias
 Do not use samples chosen at will by interviewer supervisor or director.
 Do not choose samples exclusively from particular groups such as only people you know.
 Do not restrict your sample to people living in easily accessible households. (Avoid
roadside bias).
 Do not omit households where you did not find anyone at home during first visit revisit the
later

How to avoid bias through Data Collection Methods

Biases or other systematic errors that can affect the outcomes or lead to erroneous conclusion.

Biases can be done through improper use of data collection methods. These biases and how

they can be avoided are summarized table 1 below.

Table 1: Biases, their description and how they can be avoided or minimized

Type of Bias Description of Bias How to minimise bias

Interview bias Observes are due to  Properly train data collections/

deferential measurements  interviewers
and not project effects
 Standardize interviews protocol

 Use objective and close –ended

questionnaires
Instrument or measurement Measurement errors eg non-  Standardise measurements and
bias identical instruments for instruments
different participants
 Frequently re-celebrate
 instruments
Recall bias Participants remember and  Train interviews thoroughly in
report information probing techniques to help
differently respondents remember past
events

 Use specific reference or recall

periods
Tine/ Seasonal bias Data on participants &  Standardize time for data
controls collected at collection
different times of day or
season

Source: (Passport to Research Methods)

DATA COLLECTION

DATA
Data is raw information gathered through interviews, questionnaires, observations or secondary
sources. The type of data someone intends to collect/ use will determine the statistical model to
use.

CLASSIFICATION OF DATA
 Data are classified into the following:
 Cross-sectional data
 Time series data
 Panel data
A. Cross-sectional data
o Usually contain independent observations
o Exclude time factors or contains no element of time factors, and hence is
named spot data
o Are analyzed through static models such as regression models, qualitative
models and simultaneous models
B. Time series data
– Usually contain inter-dependent observations
– Includes time factors or patterns
– Are analyzed through time series models, e.g.,
• Autoregressive Integrated Moving Average (ARIMA),
• Autoregressive Moving Average (ARMA),
 • lag or dynamic models
C. Panel Data
Hybrid of cross-sectional and time-series
• Repeated data collection on the same observation over similar time period
• Are analyzed using panel data models, e.g., Fixed and random effect models

The method of data collection in research is determined by the purpose/objective of the study,
use of research results and available resources.
Combination of methods is used since there is usually a set of objectives which require a
combination of techniques.
There are three basic data collection approaches in social research:
A. Secondary Research;
B. Survey Research; and
C. Experimental Research.
A. Secondary Research
What are secondary data?
• Secondary data are data that were collected for some purpose other than helping to solve
the current problem, whereas primary data are collected expressly to help solve the
problem at hand.
 Survey data are secondary data if they were collected earlier for another study and
primary data if they were collected for the present study.
Secondary data could be
 Internal – generated within the organization
 External – generated by outside organizations
• Potential secondary sources of information:
 Weather reports - rainfall, temperatures
 Soil maps - soil types, aerial photographs (natural vegetation)
 Population Census reports
 National Sample Survey of Agriculture
 Famine Early Warming Systems (FEWS) Publications
 Food Security and Nutrition Bulletins
 Economic Reports
  Statistical Yearbooks
 Integrated Household Surveys
 World Bank Annual Reports
 UNDP Human Development Reports
 FAO Food Production and Consumption Surveys
 Research reports
• In using the secondary data, one has to look at these aspects:
 Accuracy and reliability - should be checked by comparing data from different
secondary sources;
 Adequacy of the data - e.g. is the rainfall data daily, weekly, monthly or annual;
and
 Time period - recent data is more suitable. Socioeconomic secondary data that
are more than 5 years old should be verified.
B. Survey Research
 This is a systematic collection of information directly from respondents who are a
sample/portion of entire population.
 Survey research may be grouped into:
 Telephone Interviews - collection of information from respondents via
telephone;
 Mail Interviews - collection of information from respondents via mail or similar
technique, e.g., email; and
 Personal Interviews - collection of information in a face-to-face situation:
o Key informant interviews;
o Group interviews/Focus Group Discussions;
o Exploratory/informal/reconnaissance survey; and
o Formal or verification survey.

i. Key Informant Interviews

• Individuals knowledgeable about certain subjects or topics are asked to supply
information using a checklist.
 • Interviewee does not answer about oneself but the subject in which he/she is an expert or
has very good knowledge.
• Quality of information can be verified by interviewing two key informants about the
same subject.
• If it becomes obvious that the selected person is not knowledgeable enough,
tactfully/politely terminate interview & select another key informant.
• Consider the following factors in selecting a key informant:
• the person must have lived in the village/area for a number of years;
• the person must be the one making decisions in his/her household;
• the person must be knowledgeable about other households in the area;
• the person should be co-operative.
ii. Group Interviews
• Group interviews are useful for tapping the collective wisdom or memory of a
community.
Researcher should have a clear idea of the issue to be resolved and be able to guide or direct the
discussion but not restrict it (requires some skills).
 Use checklist: a list of key point to be collected
• Group interviews are ideal for:
– questions related to a phenomenon which uniformly affects all farmers;
controversial issues or complex issues, e.g., which are not clear from an exploratory survey
Focus Group Discussions (FGDs)
• Special type of group interviews normally to cover specific topic
• Use checklist of issues/questions to guide discussions
• Team composition:
– Moderator – conversant with the issues to guide discussions;
– Two rapporteurs – to take notes; and
– Monitor – to observe how discussions are conducted.
• Group composition:
– 15-20 individuals
 Women only
  Men only
 Youth
• Venue – conducive to relaxed interaction, avoid disturbances.
• Never take sides or say your opinion to avoid influencing members.
• Conclude by summarizing main issues discussed (one rapporteur) to ensure correct
information is collected.
• Close with friendly farewell remarks & acknowledgement members’ input.
• Duration: 45 min – 1 hour.
• Team meets at end of day to agree what has come out of discussion and produce report.
iii. Exploratory Survey
• Survey undertaken without formal sampling procedures, pretested questionnaire and
other means that permit statistical analysis.
• Main objective is to provide basic information required for the design and execution of
the formal survey
• General features:
– Physically tough;
– Requires mental and methodological flexibility;
– Information collected is mostly qualitative;
– Use checklist to collect information;
– Team effort –multidisciplinary participation and maximum interaction;
– It is an art – no substitute for experience; and
– Information could be supplemented by key informant and group interviews
ADVANTAGES AND DISADVANTAGES OF INTERVIEWS
Advantages
 People respond personally,
 The interviewer has a chance to note reactions
 Misunderstandings can be easily eliminated from both sides (feedback process)

Disadvantages
 Personal interviews are costly
 They require properly trained interviewers to avoid bias.
 iv. Formal (Verification) Survey
• Use formal methods of collecting information:
 Collect information about a population by interviewing a random sample of the
population;
 Use standardized semi-structured questionnaire – interviews conducted in a
uniform way by trained enumerators who ask questions in the same way using a
pretested written questionnaire; and
 Responses are tabulated, studied and analysed
C Experiments
• Experiments have mostly been associated with natural (hard) sciences, e.g. physics,
chemistry, biology, medicine, etc.
• Social sciences have also borrowed the experimental concepts to conduct social
experiments.

QUESTIONNAIRE

A questionnaire is a pre-formulated written set of questions to which respondents record their

answers. They are a reliable data collection tool when a researcher knows exactly what is
required and how to measure variables of interest.

Designing a questionnaire
Good design and filling of a questionnaire are a prerequisite to getting correct information. Once
a data collection tool is bad, no proper conclusions and recommendations can result from a
research process. (garbage in-garbage out)
A good questionnaire has the following attributes;
i. It is complete and concise
It obtains information required to meet survey objectives with as few questions as possible.
ii. It is reliable
A good questionnaire enables the interviewer to get the same response regardless of who asks
the question and where the question is asked. There are very few differences between
interviewers. Proper training of interviewees can enhance reliability.
iii. It provides valid data
Validity means that the question elicits a true and accurate response that measures or
explains whatever you are interested in measuring/ explaining.
iv. Ensures consistency
A good questionnaire allows an interviewer and an interviewee to interpret the meaning of
the questions in the same way.
Consistency ensures that there is a common understanding of the questions.
HOW TO DESIGN A GOOD QUESTIONNAIRE
A good questionnaire can be designed by following the following guidelines.
I. Question ordering
 Questions on the same topic should follow each other,
 General questions should be asked first,
 Responses on closed questionnaires should also be well-ordered to avoid what is referred to
as positional advantages,
 Avoid long lists of options for respondents to choose from,
 Print questionnaires with different orderings for different subsets of the sample.

OPEN AND CLOSED QUESTIONS

Open questions
Open questions are questions in which a respondent is freely allowed to give an unstructured
response.
Open questions/ responses are difficult to analyse;
 They cannot be easily quantified,
 They cannot be easily compared across the questionnaire.
They are mostly used in Focus Group Discussions.

Closed questions
Each question has a pre-determined answer of choices/options for a respondent to choose from.
Closed questions are preferred to open question;
 They are easy to code,
 They are easy to analyse.
Their major limitation is that they restrict an interviewee’s responses.

DATA ANALYSIS
  Data analysis is a process of inspecting, cleansing, transforming, and modeling data with
the goal of discovering useful information, informing conclusions, and supporting
decision-making
 The process of evaluating data using analytical and logical reasoning to examine each
component of the data provided
DATA ENTRY
 This is the process transferring information collected from a data collection instrument
(usually a questionnaire) into a computer.
• Several spreadsheets can be used including: MS Excel, SPSS, MS Access, CSPro, Stata
etc.
• At your this level, SPSS or Excel are recommended.
• Between Excel and SPSS, SPSS has the advantage that it has capabilities to label the
variables (including categorical codes) unlike Excel
• Most data entry spreadsheets/statistical packages interact with each other: one can enter
data in SPSS or Excel and analyze the data in Stata

DATA ENTRY TEMPELATE

• This is a framework that defines how your data is going to be entered.
• In most cases, the template should be drafted soon after the questionnaire is finished
(even before data collection).
• One must be careful when coming up with a template as it may affect the type of
analysis to be done.
 This comes with practice and familiarization of basic statistical procedures to be required

TYPES OF ANALYSIS
1. Univariate data –
This type of data consists of only one variable. The analysis of univariate data is thus the
simplest form of analysis since the information deals with only one quantity that changes.
It does not deal with causes or relationships and the main purpose of the analysis is to
describe the data and find patterns that exist within it. The example of a univariate data
can be height.
 Suppose that the heights of seven students of a class is recorded (figure 1),there is only
one variable that is height and it is not dealing with any cause or relationship. The
description of patterns found in this type of data can be made by drawing conclusions
using central tendency measures (mean, median and mode), dispersion or spread of data
(range, minimum, maximum, quartiles, variance and standard deviation) and by using
frequency distribution tables, histograms, pie charts, frequency polygon and bar charts.
 2. Bivariate data –
This type of data involves two different variables. The analysis of this type of data deals
with causes and relationships and the analysis is done to find out the relationship among
the two variables.Example of bivariate data can be temperature and ice cream sales in
summer season.

 Suppose the temperature and ice cream sales are the two variables of a bivariate
data(figure 2). Here, the relationship is visible from the table that temperature and sales
are directly proportional to each other and thus related because as the temperature
increases, the sales also increase. Thus bivariate data analysis involves comparisons,
relationships, causes and explanations. These variables are often plotted on X and Y axis
on the graph for better understanding of data and one of these variables is independent
while the other is dependent.
  3. Multivariate data –
the examination of more than two variables simultaneously (e.g., the relationship between
gender, race, and college graduation)

ANALYZING QUANTITATIVE DATA

Data Preparation

The first stage of analyzing data is data preparation, where the aim is to convert raw data into
something meaningful and readable. It includes four steps:

Step 1: Data Validation

The purpose of data validation is to find out, as far as possible, whether the data collection was
done as per the pre-set standards and without any bias. It is a four-step process, which includes…

 Fraud, to infer whether each respondent was actually interviewed or not.

 Screening, to make sure that respondents were chosen as per the research criteria.
 Procedure, to check whether the data collection procedure was duly followed.
 Completeness, to ensure that the interviewer asked the respondent all the questions, rather
than just a few required ones.

To do this, researchers would need to pick a random sample of completed surveys and validate
the collected data. (Note that this can be time-consuming for surveys with lots of responses.) For
example, imagine a survey with 200 respondents split into 2 cities. The researcher can pick a
sample of 20 random respondents from each city. After this, the researcher can reach out to them
through email or phone and check their responses to a certain set of questions.

Step 2: Data Editing

Typically, large data sets include errors. For example, respondents may fill fields incorrectly or
skip them accidentally.

To make sure that there are no such errors, the researcher should conduct basic data
checks, check for outliers, and edit the raw research data to identify and clear out any data points
that may hamper the accuracy of the results.

For example, an error could be fields that were left empty by respondents. While editing the data,
it is important to make sure to remove or fill all the empty fields.

Step 3: Data Coding

This is one of the most important steps in data preparation. It refers to grouping and assigning
values to responses from the survey.

For example, if a researcher has interviewed 1,000 people and now wants to find the average age
of the respondents, the researcher will create age buckets and categorize the age of each of the
respondent as per these codes. (For example, respondents between 13-15 years old would have
their age coded as 0, 16-18 as 1, 18-20 as 2, etc.)

Then during analysis, the researcher can deal with simplified age brackets, rather than a massive
range of individual ages.

QUANTITATIVE DATA ANALYSIS METHODS

Data analysis for quantitative studies involves critical analysis and interpretation of figures and
numbers, and attempts to find rationale behind the emergence of main findings

The two most commonly used quantitative data analysis methods are descriptive statistics and
inferential statistics.

DESCRIPTIVE STATISTICS

Typically descriptive statistics (also known as descriptive analysis) is the first level of analysis. It
helps researchers summarize the data and find patterns. A few commonly used descriptive
statistics are:.

Frequency Distribution
• Classification of data according to some characteristics, e.g. sex (gender), height, weight,
income, etc.
• Elements of a frequency distribution:
• Variable (what is being measured, e.g. weight, occupation)
• Frequency – the count (number) of elements in each class (category).
• See example below:
Frequency Distribution Example
Student Distribution By Sex
 Measures of Central Tendency
A measure of central tendency is a single value that attempts to describe a set of data by
identifying the central position within that set of data.

As such, measures of central tendency are sometimes called measures of central location.
They are also classed as summary statistics.

The mean (often called the average) is most likely the measure of central tendency that
you are most familiar with, but there are others, such as the median and the mode.
• These aim at coming with a single value in a data set that helps describe the
characteristics of the entire data set.
• Measures of central tendency also facilitate comparison between or among data sets, e.g.
annual mean pass rates, average yield for different areas, years, etc.
• The following are some of the common measures of central tendency:
A. Arithmetic mean

• The mean is equal to the sum of all the values in the data set divided by the number of
values in the data set. So, if we have n values in a data set and they have values x 1, x2, ...,
xn, the sample mean, usually denoted by (pronounced x bar), is:

This formula is usually written in a slightly different manner using the Greek capitol
letter, , pronounced "sigma", which means "sum of...":

65 55 89 56 35 14 56 55 87 45 92

• Where x represents the values of observations and n is the total number of observations.
B. Median
• The median is the middle score for a set of data that has been arranged in order of
magnitude. The median is less affected by outliers and skewed data. In order to calculate
the median, suppose we have the data below:

65 55 89 56 35 14 56 55 87 45 92
 • We first need to rearrange that data into order of magnitude (smallest first):

14 35 45 55 55 56 56 65 87 89 92

• Our median mark is the middle mark - in this case, 56 (highlighted in bold). It is the
middle mark because there are 5 scores before it and 5 scores after it. This works fine
when you have an odd number of scores, but what happens when you have an even
number of scores? What if you had only 10 scores? Well, you simply have to take the
middle two scores and average the result. So, if we look at the example below:

65 55 89 56 35 14 56 55 87 45

• We again rearrange that data into order of magnitude (smallest first):

14 35 45 55 55 56 56 65 87 89

• Only now we have to take the 5th and 6th score in our data set and average them to get a
median of 55.5.

C. Mode

The mode is the most frequent score in our data set. On a histogram it represents the highest bar
in a bar chart or histogram. You can, therefore, sometimes consider the mode as being the most
popular option. An example of a mode is presented below:

65 55 89 56 35 14 56 55 87 45

In this case, 55 and 56 are the modal numbers

Measures of Dispersion
A. Range
• The difference between the largest and smallest item in a data set.
• Example: Find the range the following wages 1120, 1150, 1400, 1080, 1200, 1100, and
1160.
• Range = 1400-1080 = 320

B. Standard deviation
 Measures how far observations move from their mean.
 A low standard deviation indicates that the data values tend to be closer to the mean.
 A high standard deviation indicates that the data points are spread over a wider range of
values.
 Standard deviation is given by the following formula:

Sx 
 ( x  x ) 2

n 1
Variance
• This measures the variation of the data.
• It is given by the square of the standard deviation, i.e. just remove the square root sign in
the Std. Dev. formula:

S x2 
 ( x  x ) 2

n 1
• Calculate the standard deviation and the range for the following wages 1120, 1150, 1400,
1080, 1200, 1100, and 1160.
 INFERENTIAL STATISTICS

Measures of association

A. Correlation
It measures the relationship between two variables.
Note that correlation measures the association and not the cause, i.e. correlation
shows that x is related to y and not x causes y.

B Covariance
Covariance measures the same association just like correlation

Hypothesis Testing

A. Difference between means (t-test)

• This is important when we want to compare two groups, e.g. adopters vs non-adopters,
subsidy beneficiaries vs non-beneficiaries, males vs females, etc.
• Two means may appear to be different but there is need to see whether that difference is
significantly different.
 B. Association between two categorical variables (Chi-square test)
• A chi-square test is used to test whether there is a significant difference between the
expected frequencies and observed frequencies in one or more categories.
• In other words, chi-square tests whether there is a significant relationship between the
categorical variables, e.g. gender and belonging to a club, adoption, etc.

ANALYZING QUALITATIVE DATA

Qualitative data analysis works a little differently from quantitative data, primarily because
qualitative data is made up of words, observations, images, and even symbols. Deriving absolute
meaning from such data is nearly impossible; hence, it is mostly used for exploratory research.
While in quantitative research there is a clear distinction between the data preparation and data
analysis stage, analysis for qualitative research often begins as soon as the data is available.

DATA PREPARATION AND BASIC DATA ANALYSIS

Analysis and preparation happen in parallel and include the following steps:

1. Getting familiar with the data: Since most qualitative data is just words, the researcher
should start by reading the data several times to get familiar with it and start looking for
basic observations or patterns. This also includes transcribing the data.
2. Revisiting research objectives: Here, the researcher revisits the research objective and
identifies the questions that can be answered through the collected data.
3. Developing a framework: Also known as coding or indexing, here the researcher
identifies broad ideas, concepts, behaviors, or phrases and assigns codes to them. For
example, coding age, gender, socio-economic status, and even concepts such as the
positive or negative response to a question. Coding is helpful in structuring and labeling
the data.
4. Identifying patterns and connections: Once the data is coded, the research can start
identifying themes, looking for the most common responses to questions, identifying data
or patterns that can answer research questions, and finding areas that can be explored
further.

QUALITATIVE DATA ANALYSIS METHODS

Several methods are available to analyze qualitative data. The most commonly used data analysis
methods are:

 Content analysis: This is one of the most common methods to analyze qualitative data. It
is used to analyze documented information in the form of texts, media, or even physical
 items. When to use this method depends on the research questions. Content analysis is
usually used to analyze responses from interviewees.
 Narrative analysis: This method is used to analyze content from various sources, such as
interviews of respondents, observations from the field, or surveys. It focuses on using the
stories and experiences shared by people to answer the research questions.
 Discourse analysis: Like narrative analysis, discourse analysis is used to analyze
interactions with people. However, it focuses on analyzing the social context in which the
communication between the researcher and the respondent occurred. Discourse analysis
also looks at the respondent’s day-to-day environment and uses that information during
analysis.
 Grounded theory: This refers to using qualitative data to explain why a certain
phenomenon happened. It does this by studying a variety of similar cases in different
settings and using the data to derive causal explanations. Researchers may alter the
explanations or create new ones as they study more cases until they arrive at an
explanation that fits all cases..

Data analysis is perhaps the most important component of research.

Weak analysis produces inaccurate results that not only hamper the authenticity of the research
but also make the findings unusable.

It’s imperative to choose your data analysis methods carefully to ensure that your findings are
insightful and actionable.

B. Univariate analysis
a. the examination of the distribution of cases on only one variable at a time (e.g.,
college graduation)
C. Bivariate analysis
a. the examination of two variables simultaneously (e.g., the relation between
gender and college graduation)
D. Multivariate analysis
a. the examination of more than two variables simultaneously (e.g., the relationship
between gender, race, and college graduation)
INDICATORS AND VARIABLES
 A variable is a character or quality that is observed, measured, and recorded in a
data file (generally, in a single column).
 Examples of commonly variables used in social-sciences.
 Socio-demographic variables: age, sex, religion, level of education, marital status
etc.
 Psychological variables: level of motivation, IQ, level of anxiety etc.
 Economic variables: Income, work status, household assets,
 Variables that refer to individual units other than individual:
 Birth rate, fertility rate, unemployment rate etc.
TWO BASIC TYPES OF VARIABLES

Quantitative variables – These are characters or features that are best expressed by
numerical values eg., age, number of hh members, income, etc.

Qualitative variables – These are characters or qualities that are not numerical, eg.,
mother tongue or country of origin.

WRITING RESEARCH PROPOSAL

CONTENTS OF RESEARCH PROPOSAL
WRITING RESEARCH PROPOSALS AND REPORTS

What is the purpose of a Research Proposal?

A research proposal communicates the intentions of the researcher

 the purpose of his or her intended study.

 the importance of the study.
 the step by step plan for conducting the study.

Definition: A research proposal is therefore a written plan for a study or project.

CONTENTS AND SEQUENCES FOLLOWED IN PROPOSAL AND REPORT
WRITING
Outline of a research proposal

• 1.0 Introduction

• 2.0 Literature Review

• 3.0 Methodology

• 4.0 Research Outputs

• 5.0 Work Plan

• 6.0 Budget

• 7.0 References/Bibliography

• 8.0 Appendices/Annexes

• TITLE PAGE - Consisting of proposal title, principal investigator, cooperating investigators,

complete contact details of principal investigator, proposal duration, and funds requested (1
page).

• ACRONYMS - Definition of abbreviations and acronyms (1 page).

• EXECUTIVE SUMMARY - Brief statement of the major points from each of the other sections.
The objective is to allow the reader develop a basic understanding of the proposal without
reading the entire proposal (1 page).

• TABLE OF CONTENTS - Contains page numbers of chapter titles and their sub-headings (1-2
pages).

• LIST OF TABLES - Contains titles of tables and their page numbers (1-2 pages).

• LIST OF FIGURES - Contains titles of figures and their page numbers (1 – 2 pages).

INTRODUCTION (4-5 pages)

• Problem Definition – Statement of the Problem and the factors that influence it (2-3 pages)

• Justification/Rationale – why the research is important (1 page)

• Objectives – what the research intends to achieve. Objectives should be SMART as much as
possible (0.5 page)

– Underlying Objective – main or general objective

– Specific Objectives

• Hypotheses/Research Questions – propositions to be tested/questions to be answered (0.5

page)

LITERATURE REVIEW (3 pages)

 • Review information related to your research area that has been presented by other researchers
or institutions.

• Best approach is to separate Literature Review into three themes:

– Historical and descriptive: what research has been done on the topic

– Methodological: data collection and analytical methods used by others explaining why
they are suitable for your study; and

– Results, interpretation and controversy: – summarize main results and interpretations

of other studies (in own words) discussing how your research fits in and their
weaknesses.

• Avoid plagiarism by acknowledging your sources using citations, footnotes, references or

bibliography (Literature Review will be discussed in detail later).

METHODS (3 – 5 pages)

• Study Area – location of study area and why it is selected

• Sources of information – primary and secondary sources

• Data collection methods – e.g., key informant interviews, focus group discussions,
exploratory/informal survey, formal survey

• Sampling method - simple random sampling, systematic sampling, stratified sampling, cluster
sampling, multi-stage sampling

• Sample size – determination of sample size

• Measurement Instruments – instruments that will be used, normally questionnaire(s) and

checklists and their pre-testing

• Quality control measures

• Recruitment and Training of Enumerators and Supervisors

• Field Supervision

• Data Cleaning and Entry

• Analytical Techniques

• Descriptive analyses: e.g., means, percentages, correlations)

• Quantitative analyses: e.g., regression models

• Computer packages: e.g., SPSS, Stata, Epi Info, Eviews, etc.

RESEARCH OUTPUTS AND IMPACTS (1-2 pages)

• Anticipated key accomplishments and how they will be disseminated (1-2 pages)
5.0 WORK PLAN AND LABOUR INPUT (2 – 3 pages)

• Work plan - indicates when main activities will be carried out, normally presented in a chart
form (1 – 2 pages).

Labour input - gives person days and cumulative person days required for the main activities (1 page

BUDGET (1 – 3 pages)

• Transport

• Field allowances for accommodation and meals (per diem)

• Materials (e.g., stationery, equipment, etc)

• Computer time

• Fee/Honoraria

• Overhead (%)

REFERENCES OR BIBLIOGRAPHY (2-4 pages)

• Present all literature cited in the text in the case of References;

• Present all literature cited in the text as well as other literature not cited in the text in the case
of Bibliography;

• Present alphabetically.

APPENDICES

• Include relevant material excluded in the main text of the proposal

1. Title
 A research Proposal or Project must have a title.
 A title should be explicit and should contain key words that capture the intention of the
researcher.
 Should avoid abbreviations.

2. Introduction
Introduces the main theme of the research or project.

Usually contains a problem statement and background to the research or project.

3. Literature Review
 Provides references on the technical and scientific basis of the proposed work.
  Helps the researcher to focus the research more on certain aspects that are found in the already
published studies (especially those that are not very clear or those that require further
research).

WRITING RESEARCH PROPOSALS AND REPORTS

What is the purpose of a Research Proposal?

A research proposal communicates the intentions of the researcher

 the purpose of his or her intended study.

 the importance of the study.
 the step by step plan for conducting the study.
Definition: A research proposal is therefore a written plan for a study or project.

CONTENTS AND SEQUENCES FOLLOWED IN PROPOSAL AND REPORT

WRITING
4. Title
 A research Proposal or Project must have a title.
 A title should be explicit and should contain key words that capture the intention of the
researcher.
 Should avoid abbreviations.

5. Introduction
Introduces the main theme of the research or project.

Usually contains a problem statement and background to the research or project.

6. Literature Review
 Provides references on the technical and scientific basis of the proposed work.
 Helps the researcher to focus the research more on certain aspects that are found in the already
published studies (especially those that are not very clear or those that require further
research).

7. Justification
 Also known as rationale to the study or project.
 Explains why the project is important and how it contributes to certain goals.

8. Objectives
 Are operationalized goals that specify the central results expected.
 Identifies the central theme or concern of study or research or project.
 Should be well defined.
 Should be matched to indicators (For monitoring and evaluation purposes)

9. Hypothesis
Describe statements to be proved or disapproved.

10. Methodology
Includes the methods, tools and approaches one is going to use in order to carry out ones work e.g.
sampling procedure, data collection tools and methods, statistical analysis of the data or other
logistical aspects of the proposed work.

11. Results
Are outputs, effects and impacts resulting from a project or research.

12. Discussions
Involves discussion and interpretation of results in terms of objectives and hypotheses.
 One also reports on key issues.

13. Conclusion
Summarises the findings in relation to the objectives.

Provides a concrete output from ones work.

14. Recommendations
State the limitations and main activities that ought to be done as a follow-up to the study or project
or research.

15. References/Bibliography
Provides literature cited in alphabetical order of first authors.

Mwanza J. (2005), Research Methods Monitoring and Evaluation: A Reference Manual for students

Broadway L. (1997), Economics of Finance.

London: International Publishers.

16. Justification
 Also known as rationale to the study or project.
 Explains why the project is important and how it contributes to certain goals.

17. Objectives
 Are operationalized goals that specify the central results expected.
 Identifies the central theme or concern of study or research or project.
 Should be well defined.
 Should be matched to indicators (For monitoring and evaluation purposes)

18. Hypothesis
Describe statements to be proved or disapproved.

19. Methodology
Includes the methods, tools and approaches one is going to use in order to carry out ones work e.g.
sampling procedure, data collection tools and methods, statistical analysis of the data or other
logistical aspects of the proposed work.
20. Results
Are outputs, effects and impacts resulting from a project or research.

21. Discussions
Involves discussion and interpretation of results in terms of objectives and hypotheses.

One also reports on key issues.

22. Conclusion
Summarises the findings in relation to the objectives.

Provides a concrete output from ones work.

23. Recommendations
State the limitations and main activities that ought to be done as a follow-up to the study or project
or research.

24. References/Bibliography
Provides literature cited in alphabetical order of first authors.

Mwanza J. (2005), Research Methods Monitoring and Evaluation: A Reference Manual for students

Broadway L. (1997), Economics of Finance.

London: International Publishers.

THE PROJECT CYCLE

PROJECT
A project is a coordinated set of interventions over time, to move from a present situation to a
future one that is perceived to be better. A project is therefore an instrument of change.

The Project Cycle

This shows all the stages of a project from start to completion. Diagrammatically these stages are
as follows:

Identification
 Evaluation
Preparation

Implementation
(Monitoring) Appraisal

1. Identification (Conceptualization)
Finding potentially fundable projects. Sources of information are
 Local leaders
 Politicians
 Existing projects
 Sector studies
 Communities (ordinary people)

2. Preparation
Stage where objectives, activities and other requirements are outlined which would lead
to the realization of the goal(s)
 Identify the goal
 Draw the objectives and their corresponding activities

3. Appraisal
 Involves evaluation of the alternatives options/actions (called ex-ante analysis)
 Involves critical review by an independent team
 Approval or rejection is the outcome

4. Implementation
Has stages as follows:
 Investment period – when all inputs are assembled/purchased
 Development period – when inputs begin showing results
 Monitoring – to ensure that we are on the right track
  Completion – when all activities have been completed

5. Evaluation (Ex-post analysis)

 Measures elements of success or failure
 Usually done by an independent team
 Can be mid-term or final evaluation
Note: In some books identification and preparation are combined into Design stage

Aspects to consider in all stages of a project before implementation

 Technical aspects (the design, the inputs etc.)
 Institutional aspects – tenure, relevant organizations, managerial aspects etc
 Social aspects – broader implications e.g. gender roles, employment opportunities
 Commercial and business aspect – e.g. market security and securing supplies

Some reasons why projects fail:

 Lack of ownership
 Problems of design e.g. wet vs dry rations for baby food
 Administrative and managerial aspects e.g. frequent hiring and firing,
 Changing economic and marketing environment
 Unrealistic targets
 Externally driven initiatives
MONOTORING AND EVALUATION OF DEVELOPMENT PROJECTS

MONITORING
Monitoring is the process of routinely gathering information on all aspects of a project and
utilizing this information in project management and decision making.
A monitoring plan should serve to provide essential information and act as a basic and vital
management tool. To fulfil this role, a monitoring plan must include systems for:
 Acquiring information on key project areas
 Summarizing information
 Analyzing information and
 Utilizing this information to make decisions

In addition to the above, information obtained from monitoring can contribute to:
 Demonstrating innovative and effective strategies
 Generating financial and other support and
 Marketing the institution

What do we Monitor?
(a) Progress and effectiveness of project activities - training, meetings, outreach activities
(b) Use of resources – finances, commodities, equipment, staff etc.
(c) Timing – schedules, deadlines, achievement of work plans
(d) Results – achieving objectives, coverage, impact on beneficiaries

Why do we Monitor?
Information from monitoring enables project managers to know
(a) How activities are progressing, whether on track or not
(b) Whether strategies used are effective
(c) Establish the need for materials and/or technical support
(d) To feed into evaluation

Characteristics of a good monitoring system

 Must be an integral part of the project plan
 Allows for the timely collection of information
 Uses what it collects and collects what it uses
 Allows for a two way flow of information

Steps in developing a project monitoring system

(1) Identify the specific information needed for planning, monitoring and evaluation of the
project
(2) Identify the source or sources from which you will obtain the required or desired information
including the methodology or tool required
(3) Identify and train the persons who will be responsible for collecting the information
(4) Determine the frequency of collecting information
(5) Design forms/procedures for collecting information
(6) Establish systems for summarizing, tabulating and analyzing the information

Reporting
This is very important and project managers need to regularly provide reports to stakeholders.
The aims of these reports are:
 To inform stakeholders of progress and constraints encountered so that remedial or corrective
action can be taken
 To provide a formal documented record of achievement
 Facilitate future reviews and evaluation
 Promote transparency and accountability
EVALUATION
Definition: Evaluation involves a systematic, objective analysis of a project’s relevance,
efficiency, effectiveness, impact in relation to objectives, sustainability.

The ultimate purpose is to:

(a) draw lessons from experience to improve the quality of a project (especially true for mid-
term evaluation)
(b) improve the design of similar future projects
(c) demonstrate the project’s merit to staff, beneficiaries, funders and others

Some more specific reasons for Evaluations:

 Hear from project beneficiaries and assess impact
 For accountability purposes
 Assess achievements of objectives compared to targets set
 Assess effectiveness of strategies set
 Identify lessons for sharing
 Assess staff performance
 Decision making for future of project
 Influence policies

Important Terms in Evaluation

Relevance:
 To government and donor policies
 To identified key stakeholders or target group
 To identified problems

Efficiency:
Focuses on how well various activities transformed available resources into intended
outputs/results in terms of quantity, quality and timeliness. Efficiency therefore focuses on the
following:

The quality of day to day management of

 budget
 management of personnel and property
 adequacy in managing risks e.g. level of flexibility
 respect for deadlines

Cost and value for money

 How far the costs of the project were justified by the results (one can also compare with
similar projects elsewhere)
Effectiveness:
Concerned with how far the project’s outputs were used by the beneficiaries and how far the
intended goals were met. It analyses the following:

 whether all planned benefits have delivered and received as perceived by ALL stakeholders
and not implementers only
 whether there were any patterns of behavioural change among the target group and hoe these
have produced planned improvements
 if assumptions or risks turned out to be true or not
 how unplanned outcomes or experiences may have affected results

Impact:
the extent to which the benefits received by the target group had a wider overall effect on larger
numbers of people in the area, sector etc. An important aspect of impact is sustainability.

Sustainability:
Relates to whether the positive outcomes of the project are likely to continue after external
assistance ands. Analysis of this will focus on:
 ownership of objectives and achievements
 whether products or services provided were affordable for the intended beneficiaries
PARTICIPATORY MONITORING AND EVALUATION
Participatory monitoring and evaluation is when beneficiaries are also involved in the processes
besides staff and external people. Beneficiaries and other stakeholders are involved in the design,
implementation and analysis of the results.

Participatory monitoring and evaluation must begin rights at the design stage of the project.
Beneficiaries will be part of the planning process and will therefore among other things, be
familiar with the monitoring tool as well as the bench marks set. Beneficiaries must have copies
of the project write up to enable them follow up and track progress.

Regular formal meetings must be scheduled where all concerned can compare notes on progress
of the project in case of monitoring and progress of the process in case of evaluation. If it is a
construction project, it may be advisable to have what are called “Site Meetings”. These are
meetings that take place right at the site of construction and targets agreed during the previous
meeting are reviewed. Contractors involved must be part of such meetings.

Why should we involve beneficiaries?

 Communities are principal stakeholders and they understand their situation including
constraints better than us all
 They are the custodians of most of the resources and knowledge required for rural
development e.g. land, labour etc.
 Usually have experience with past or previous projects (whether they failed or succeeded.

Why should we involve project staff?

 beneficiaries may be more open to talk to these than to external staff
 To ensure continuity and corrective action is taken quickly since staff will be familiar with
concerns raised
 Project staff understand the activities and objectives of the project
 It is a capacity building experience for them

Why should we involve external evaluators?

 They are not biased in their assessment
 Provide a broader view of impact - because most of these are a lot of experience with other
similar projects elsewhere
 Enhance donors confidence – because donors believe that by involving external people you
demonstrate that you have nothing to hide
 They give strong recommendations
 Staff feel secure to give negative feedback about the project to these
 Could benefit from their links to other potential collaborators.
Monitoring and Evaluation Compared

Programme/Project Monitoring Programme/Project Evaluation

Frequency Regular Periodic

Main Action Keeping track Appraisal

Basic Purpose Improve progress in Improve relevance, effectiveness,

implementation impact, future programming

Duration Short term Long term

Focus in programme Inputs, process, outputs Inputs, process, outputs, outcomes,

cycle impacts

References for Work plans, performance targets, Programme objectives and strategy,
comparison reference indicators performance targets, widely
accepted benchmarks

Information sources Routine systems, field Same, plus specific surveys, studies
observation, progress reports,
rapid assessments

Undertaken by Programme managers, Same, plus external evaluators

community workers, primary
stakeholders, supervisors,
funding organizations

Reporting to Programme managers, Same, plus policy-makers, wider

community workers, primary range of external stakeholders
stakeholders, supervisors,
funding organizations