2/7/2025 1

Writing The Winning Thesis Or

Dissertation

Ethiopian Civil Service University

Directors Of Research Affairs

Graduate Students Research

Coordination Unit
2/7/2025 2

Topics

YOUR RESEARCH TOPIC

YOUR YOUR
METHODOLOGY PROPOSAL

YOUR LITERATURE
2/7/2025 3

Characteristics of a Good Research Topic:

The Research topic 1. Relevance: The topic should be meaningful a
contribute to the field of study.
2. Clarity: The topic should be clearly defined,
The Research topic making it easy to understand the research
focus.
3. Manageability: The scope should be narrow
• A research topic is a specific enough to allow in-depth analysis within the
subject or issue that a researcher’s time and resource constraints.
researcher chooses to study, 4. Interest: The researcher should have a genui
analyze, and explore through interest in the topic, as this can drive
motivation and engagement.
systematic investigation.
5. Originality: A good topic often addresses ga
in existing knowledge or offers a fresh
perspective on known issues.
2/7/2025 4

Examples Of Research Topics And How To Narrow Them Down

Examples Examples
• Broad Topic: “The Impact of Social • Broad Topic: “Climate Change and
Media on Society” Environmental Policy”
• Narrowed Topic: “The Effects of • Narrowed Topic: “The Role of
Social Media Usage on Adolescent Renewable Energy Policies in
Self-Esteem” Reducing Urban Air Pollution”

• Explanation: The narrower topic • Explanation: This version narrows

focuses specifically on adolescents, the focus to urban settings and air
making it more manageable and pollution, making it a more specific
targeted. and researchable topic.
2/7/2025 5

Research topic and research methods

Topic one
Topic one
• Explanatory
• Assessment type

• Social Media Usage, Prevalence of Social

• The Effects of Social Media Usa
Media Addiction Among Undergraduate on Adolescent Self-Esteem.
Students of St. Mary's University.
• Beyond description you may use correlati
and regression analysis
• Simple descriptive statistical tools can be
used to address this research agenda
such as frequency, percentage, mean etc
2/7/2025 6

Mediating variables If something is a mediator:

• A mediator is a way in which an • It’s caused by the independent variable.
• It influences the dependent variable
independent variable impacts a
dependent variable. • When it’s taken into account, the statistical
correlation between the independent and
dependent variables is higher than when it
isn’t considered.

• It’s part of the causal pathway of an • Mediation analysis is a way of statistically

testing whether a variable is a mediator
effect, and it tells you how or why an using linear regression analyses or
effect takes place. ANOVAs. You may statistical software
AMOS , IBM SPSS WITH PROCESS
MODEL
2/7/2025 7

Example: Mediator variables

• The effect of socioeconomic status

on students reading ability, the
mediating role of parental education
levels.
2/7/2025 8

Moderating variables
A moderator
A moderator • Moderators usually help you judge th
external validity of your study by
• influences the level, direction, or identifying the limitations of when th
presence of a relationship between relationship between variables holds.
variables.
• For example, while social media use c
• It shows you for whom, when, or predict levels of loneliness, this
under what circumstances a relationship may be stronger for
relationship will hold. adolescents than for older adults. Ag
a moderator here.
2/7/2025 9

Example: Moderator variables Example: Moderator variables

• In a study on work experience and

salary, you hypothesize that:

• Gender identity moderates the

relationship between work experience
and salary.

• This means that the relationship

between years of experience and salary
would differ between men, and women
2/7/2025 10
2/7/2025 11

Your Research Proposal

2/7/2025 12

Your Research Proposal …

Title page
Background and justification
• Like your dissertation or thesis, the • The background of the study explains the
broader context of the research problem.
proposal will usually have a title
page that includes: • It provides information on the current state
of knowledge, relevant historical
• The proposed title of your project
developments, gaps in existing research, and
the significance of addressing these gaps.
• Your name
• Your supervisor’s name • This section often precedes the problem
• Your institution and department statement and serves as a foundation for
understanding why the research is
necessary.
2/7/2025 13

Importance of the Background of the Study

Background and justification
• Establishes Context: It situates the research within its
• Purpose: broader academic or practical framework.
• Justifies the Research: By highlighting gaps or
unresolved issues, it demonstrates why the study is
• To introduce the topic and establish its
necessary.
relevance.
• Engages the Reader: A well-written background builds
• To summarize existing research and
identify knowledge gaps. interest and understanding, preparing the reader for
the study’s objectives.
• To explain the motivation and rationale
behind the study. • Links to the Research Problem: It transitions smoothly
into the problem statement, laying the groundwork for
the research questions or hypotheses.
2/7/2025 14

Step 2: Identify the Key Elements

How to Write the Background of the Study

• Step 1: Understand the Research • A strong background includes the

Topic following components:
• Introduction to the Topic: Briefly describe
• Before writing, ensure you have a the area of study and its importance.
thorough understanding of your • Current Knowledge: Summarize what is
topic. Familiarize yourself with key already known from previous research.
concepts, theories, and previous • Knowledge Gaps: Identify limitations or
studies. gaps in existing studies.
• Relevance of the Study: Explain why
addressing these gaps is significant.
2/7/2025 15

Step 3: Organize the Content

Step 4: Write Concisely and Clearly

• Structure the background logically: • Avoid overly technical language or

• Start Broadly: Begin with general
excessive detail.
information about the topic.
• Narrow the Focus: Gradually narrow • Your goal is to provide enough context to
down to the specific problem your inform and engage the reader without
research addresses. overwhelming them.
• End with a Rationale: Conclude with a
clear statement of why your study is
essential.
2/7/2025 16

Problem Statement
Problem Statement Importance of a Problem Statement

• A problem statement is a concise description 1. Focuses the Research: Clearly defines the
of the issue or challenge that a research issue to be investigated.
project or initiative aims to address.
2. Highlights Significance: Demonstrates why
the problem is important to address.
• It defines the problem in clear terms and
3. Aligns Objectives: Ensures the research goa
establishes its significance, providing a
foundation for developing objectives, are connected to real-world challenges.
methodologies, and potential solutions. 4. Guides Methodology: Shapes the design an
approach of the study.
• Writing a well-defined problem statement is 5. Supports Decision-Making: Helps
crucial for setting the direction of research stakeholders understand the context and
and ensuring its relevance. urgency of the issue.
2/7/2025 17

Types of Problem
Statements
2. Business Problem Statements
• 1. Academic Problem Statements

• Purpose: Defines operational,

• Purpose: Used in research papers or
financial, or strategic issues within
theses to identify gaps in knowledge or
an organization.
unresolved issues.

• Example: • Example:
• “While many studies have explored the • “The company has experienced a 25%
psychological effects of social media on decline in customer retention over the
teenagers, limited research exists on its past year due to outdated customer
impact on their critical thinking skills.” engagement strategies.”
2/7/2025 18

3. Social or Policy Problem Statements 4. Technical Problem Statements

• Purpose: Focuses on societal • Purpose: Identifies challenges related to

challenges, policies, or public issues. technological development or

implementation.

• Example: • Example:

• “The lack of affordable housing in • “The current software application fails to

urban areas has resulted in handle large-scale data processing

efficiently, leading to delays in analysis.”
increased homelessness and
economic inequality.”
2/7/2025 19

Elements of a Problem Statement

• Current Situation: Describe the existing • Significance: Explain why the problem
context or conditions. matters and its potential impact.

• Example: “This can lead to reduced

• Example: “Remote work has become the
productivity, lower employee satisfaction,
norm for many businesses in the post-
and missed deadlines.”
pandemic era.”
• Desired Outcome: Outline the ideal state or
• Problem Description: Define the specific solution.
issue or challenge.
• Example: “Implementing better
• Example: “However, teams often struggle to communication tools and strategies can
maintain effective communication and enhance team dynamics and improve
collaboration in virtual settings.” performance.”
2/7/2025 20

Steps to Write a Problem Statement

1-IDENTIFY THE PROBLEM 2. UNDERSTAND THE CONTEXT

• Pinpoint the issue or gap that • Gather background information to

requires attention. provide context.
• Use specific data or observations to
support the claim. • Example: “The delays are primarily
caused by inefficiencies in the
• Example: “Customer complaints warehouse inventory system.”
about delayed deliveries have
increased by 40% in the past six
months.”
2/7/2025 21

3. DEFINE THE IMPACT 4. PROPOSE THE IDEAL SOLUTION

Highlight how the problem affects • Describe what the situation would
stakeholders, such as individuals, look like if the problem were
organizations, or communities. resolved.

Example: “This has resulted in • Example: “Upgrading the inventory

decreased customer satisfaction and a management software can
potential loss of market share.” streamline operations and ensure
timely deliveries.”
5. KEEP IT CONCISE AND CLEAR
• Avoid jargon and excessive details.
• Aim for 4–5 sentences that succinctly convey the problem and its significance.
2/7/2025 22

Questions and objectives Questions and objectives

Perhaps the most important part of your • If your research aims to test
ntroduction is your questions and hypotheses, you can formulate them
objectives, as it sets up the expectations here.
or the rest of your thesis or dissertation.
• Your introduction is also a good place
How you formulate your research for a conceptual framework that
questions and research objectives will suggests relationships between
depend on your discipline, topic, and variables.
ocus, but you should always clearly state
he central aim of your research.
2/7/2025 23

Does conceptual frame work has relationship with research

objective, literature and method and result

• A conceptual framework illustrates

the expected relationship between
your variables.

• It defines the relevant objectives for

your research process and maps out
how they come together to draw
coherent conclusions.
2/7/2025 24

Developing a conceptual framework in research

Tip
Step 1: Choose your research question

ou should construct your conceptual • Your research question guides your work
ramework before you begin collecting your determining exactly what you want to fin
ata. out, giving your research process a clear
focus.
onceptual frameworks are often
epresented in a visual format and • Example: Research question
lustrate cause-and-effect relationships. • Let’s say you want to study whether
students who study more hours get high
ou can start conceptualizing this as you exam scores. To investigate this question
etermine your relevant paper, thesis, or you can use methods such as an experim
issertation topic. or a survey to test the relationship betwe
variables.
2/7/2025 25

p 2: Select your independent and dependent

Example: Variables
iables
• In order to move forward with your • Following our example:
• The expected cause, “hours of study,” is the
research question and test a cause- independent variable (the predictor, or explana
and-effect relationship, you must variable)
first identify at least two key
variables: your independent and • The expected effect, “exam score,” is the
dependent variable (the response, or outcome
dependent variables. variable).

• In other words, you suspect that “exam score”

depends on “hours of study.” Thus, your
hypothesis will be that the more hours a studen
studies, the better they will do on the exam.
2/7/2025 26

Step 3: Visualize your cause-and-effect

relationship

Now that you’ve figured out your research question

and variables, the first step in designing your
onceptual framework is visualizing your expected
ause-and-effect relationship.

We demonstrate this using basic design components

of boxes and arrows. Here, each variable appears in
a box.

To indicate a causal relationship, each arrow should

tart from the independent variable (the cause) and
point to the dependent variable (the effect).
2/7/2025 27

ep 4: Identify other influencing

riables
Focus and scope
It’s crucial to identify other variables • After a brief introduction to your
that can influence the relationship general area of interest, narrow your
between your independent and focus and define the scope of your
dependent variables early in your research. You can narrow this down
research process. in many ways, such as by:

Some common variables to include • Geographical area

• Time period
are moderating, mediating, and
• Demographics or communities
control variables.
• Themes or aspects of the topic
2/7/2025 28

Key Features:
Limitations in Research 1.Acknowledged
Weaknesses: Reflect the challenges
• Limitations are factors that restrict the faced during the research process.
scope, methodology, or interpretation of
research findings. 2.Context-Specific: Vary depending
on the research design,
• They arise due to constraints such as methodology, or field of study.
time, resources, design choices, or
3.Enhance Credibility: By addressing
external influences beyond the
researcher’s control. limitations, researchers demonstrate
critical thinking and transparency.
• While limitations do not necessarily • Example: Limited sample size in a
invalidate a study, they highlight areas
for improvement or further survey study may reduce the
investigation. generalizability of the results to a
broader population.
2/7/2025 29

Types of Limitations in Research

1. Methodological Limitations 2. Sample Size and Composition

• Description: Constraints related to • Description: Issues with the number

the research methods used. or characteristics of participants in
• Examples: the study.
• Use of a non-random sampling • Examples:
technique. • Small sample sizes reduce statistical
• Reliance on self-reported data, which power.
can introduce bias. • Sampling bias occurs when the sample
• Impact: Affects the accuracy or is not representative of the population.
reliability of the data collected. • Impact: Limits the generalizability of
the findings.
2/7/2025 30

3. Time Constraints 4. Resource Limitations

• Description: Insufficient time to • Description: Constraints on

conduct research thoroughly. financial, technological, or human
• Examples: resources.
• Limited duration of an experiment. • Examples:
• Inability to collect longitudinal data • Inability to afford advanced equipment
due to time restrictions. for data collection.
• Impact: Affects the depth of the • Insufficient access to databases or
analysis and the ability to explore archival materials.
trends over time. • Impact: Limits the scope of data
collection and analysis.
2/7/2025 31

5. External Influences 6. Ethical Limitations

• Description: Factors beyond the • Description: Restrictions due to

researcher’s control that impact the ethical considerations and
study.
guidelines.
• Examples:
• Examples:
• Changes in political or economic
conditions during the study. • Inability to experiment on certain
• Unexpected interruptions, such as populations due to ethical constraints.
natural disasters or pandemics. • Limited access to sensitive or
• Impact: May introduce variability or confidential data.
disrupt data collection. • Impact: Restricts the scope and
design of the study.
2/7/2025 32

7. Theoretical Limitations Examples of Research

Limitations
• Description: Constraints related to • Example 1: Survey Study
the theoretical framework or
assumptions used. • Research Topic: Effects of social media on
• Examples: mental health.

• Dependence on outdated theories.

• Limitation: The study used a convenience
• A narrow focus on a specific aspect of
sampling method, leading to a sample
a complex phenomenon. dominated by young adults, limiting its
• Impact: Limits the applicability of applicability to older populations.
findings to broader contexts.
2/7/2025 33

Common Mistakes to Avoid

• Ignoring Limitations: Failing to address
limitations can appear dishonest or
careless.

• Overemphasizing
Weaknesses: Excessive focus on
limitations may overshadow the study’s
contributions.

• Being Defensive: Avoid justifying

limitations with excuses; instead,
explain them objectively.

• Generalizing Findings: Be cautious

about making broad claims when
limitations restrict generalizability.
2/7/2025 34

Significance of the study

• Depending on your field, the • Ultimately, your introduction should
importance of your research might explain how your thesis or dissertatio
focus on its practical application
(e.g., in policy or management) or • Helps solve a practical or
theoretical problem
• on advancing scholarly • Addresses a gap in the literature
understanding of the topic (e.g., by • Builds on existing research
developing theories or adding new
• Proposes a new understanding o
empirical data).
your topic

• In many cases, it will do both.

2/7/2025 35

How To Write A Literature Review

 2/7/2025 36

A Literature Review………..
What is the purpose of a literature
What is a literature review?
review?
A literature review is a survey • Demonstrate your familiarity with the topic and
its scholarly context. Develop a theoretical
f scholarly sources on a specific
framework and methodology for your research.
opic.
• Position your work in relation to other
t provides an overview of current researchers and theorists. Show how your
research addresses a gap or contributes to a
nowledge, allowing you to identify debate.
elevant theories, methods, and gaps
n the existing research that you can • Evaluate the current state of research and
ater apply to your paper, thesis, demonstrate your knowledge of the scholarly
r dissertation topic. debates around your topic.
2/7/2025 37

A Literature Review………..
Step 1 – Search for relevant literature

• Before you begin searching for • Make a list of keywords

literature, you need a clearly defined
topic.
• Start by creating a list of keywords
related to your research question.
• If you are writing the literature
Include each of the key concepts or
review section of a dissertation or
research paper, you will search for variables you’re interested in, and
literature related to your research list any synonyms and related terms.
problem and questions.
2/7/2025 38

A Literature Review………..
Step 2 – Evaluate and select sources
Step 3 – Identify themes, debates, and gaps
• For each publication, ask yourself:
• What question or problem is the author
addressing? • To begin organizing your literature
• What are the key concepts and how are they review’s argument and structure, be sure
defined? you understand the connections and
• What are the key theories, models, and methods? relationships between the sources you’ve
• Does the research use established frameworks or read.
take an innovative approach?
• What are the results and conclusions of the
study? • Based on your reading and notes, you can
• How does the publication relate to other look for:
literature in the field? Does it confirm, add to, or
challenge established knowledge?
• What are the strengths and weaknesses of the
research?
2/7/2025 39

Trends and patterns (in theory, method or

esults): do certain approaches become more Step 4 – Outline your literature review’s
or less popular over time? structure

• There are various approaches to organizing

Themes: what questions or concepts recur
across the literature? the body of a literature review.

• Depending on the length of your literature

Debates, conflicts and contradictions: where
do sources disagree? review, you can combine several of these
strategies.
• Chronological
Pivotal publications: are there any influential
heories or studies that changed the direction • Thematic
of the field? • Methodological
• Theoretical
Gaps: what is missing from the literature? Are
here weaknesses that need to be addressed?
2/7/2025 40

Strategies…

Chronological Thematic

• The simplest approach is to trace the • If you have found some recurring
development of the topic over time. central themes, you can organize your
However, if you choose this strategy, be literature review into subsections that
careful to avoid simply listing and address different aspects of the topic.
summarizing sources in order.
• For example, if you are reviewing
• Try to analyze patterns, turning points literature about inequalities in migrant
and key debates that have shaped the health outcomes, key themes might
direction of the field. Give your include healthcare policy, language
interpretation of how and why certain barriers, cultural attitudes, legal status,
developments occurred. and economic access.
2/7/2025 41

Strategies…
Methodological
• If you draw your sources from different Theoretical
disciplines or fields that use a variety of
research methods, you might want to • A literature review is often the foundatio
compare the results and conclusions for a theoretical framework.
that emerge from different approaches.
• You can use it to discuss various theories
• For example: models, and definitions of key concepts.
• Look at what results have emerged in
qualitative versus quantitative research. • You might argue for the relevance of a
• Discuss how the topic has been approached specific theoretical approach, or combine
by empirical versus theoretical scholarship
various theoretical concepts to create a
• Divide the literature into sociological,
framework for your research.
historical, and cultural sources.
2/7/2025 42
2/7/2025 43

Step 5 – Write your literature review

• Like any other academic text, your • Introduction

literature review should have an • Body of your literature
introduction, a main body, and a • Theoretical
conclusion. • Imperial
• Gap
• What you include in each depends • CFW (OPTIONAL )
on the objective of your literature
review.
2/7/2025 44

RESEARCH METHODS
2/7/2025 45

YOUR RSEARCH APPROACH

Quantitative research Qualitative research
Quantitative research is expressed in numbers • Qualitative research is expressed in words.
and graphs. It is used to test or confirm theories
and assumptions. It is used to understand concepts, thoughts
or experiences. This type of research
This type of research can be used to enables you to gather in-depth insights on
establish generalizable facts about a topic.
topics that are not well understood.
Common quantitative methods
nclude experiments, observations recorded as
numbers, and surveys with closed-ended • Common qualitative methods include
questions. interviews with open-ended questions,
observations described in words,
Quantitative research is at risk for research and literature reviews that explore concepts
biases including information bias, omitted
variable bias, sampling bias, or selection bias. and theories.
2/7/2025 46

MIXTED RESEARCH • Mixed methods research combines elements

APPROACH of quantitative research and qualitative research in
order to answer your research question.

• Mixed methods can help you gain a more complete

Mixed picture than a standalone quantitative or qualitative
methods study, as it integrates benefits of both methods.
research
• Mixed methods research is often used in the
behavioral, health, and social sciences, especially in
multidisciplinary settings and complex situational or
societal research.
2/7/2025 47

Reasons for using

mixed methods • Generalizability: Qualitative research usually has a
smaller sample size, and thus is not generalizable. In
research mixed methods research, this comparative weakness
is mitigated by the comparative strength of “large
N,” externally valid quantitative research.

Generalizability • Contextualization: Mixing methods allows you to

put findings in context and add richer detail to your
Contextualization conclusions. Using qualitative data to illustrate
Credibility quantitative findings can help “put meat on the
bones” of your analysis.

• Credibility: Using different methods to collect data

on the same subject can make your results more
credible. This process is called triangulation.
2/7/2025 48

Mixed Methods Study Designs

Convergent (parallel or concurrent) design: A mixed methods design in which quantitative and
qualitative data are collected simultaneously but analyzed separately, and the results are merged or
ntegrated. This type of design allows for the collection of rich, detailed data and provides a
omprehensive understanding of the research problem.
2/7/2025 49

Sequential (exploratory or
explanatory) designs:
• Exploratory sequential design: This techniqu
• In this type of mixed methods design, the involves the initial collection of qualitative da
aim is to use the results of one method to and the findings are used to guide the design
develop or build another method. and development of quantitative data collect
tools
• These designs may begin with a qualitative
method followed by a quantitative approach • Explanatory sequential design: this method i
(exploratory) or a quantitative investigation characterized by the collection and analysis o
followed up with a qualitative enquiry quantitative data, followed by the collection
(explanatory). and analysis of qualitative data.The goal is to
use the qualitative findings to explain and
interpret the quantitative results .
2/7/2025 50

Exploratory sequential mixed methods design

2/7/2025 51

Population and Sampling Methods

When Is Data Collection From a Population
Population Preferred?
• The research population, also known as the
target population, refers to the entire group
or set of individuals, objects, or events that 1. Small or Accessible Population
possess specific characteristics and are of 2. Census or Complete Enumeration
interest to the researcher.
3. Unique or Critical Characteristics
• It represents the larger population from 4. Legal or Regulatory Requirements
which a sample is drawn.
5. Precision or Accuracy
• The research population is defined based on Requirements
the research objectives and the specific
parameters or attributes under
investigation.
2/7/2025 52

Population and Sampling Methods

Sampling
• The sample is the group of individuals
who will actually participate in the
research.

• To draw valid conclusions from your

results, you have to carefully decide how
you will select a sample that is
representative of the group as a whole.

• This is called a sampling method. There

are two primary types of sampling
methods that you can use in your
research:
2/7/2025 53

Population and Sampling Methods

Sampling frame
• The sampling frame is the actual list • Example: Sampling frame
of individuals that the sample will be • You are doing research on working
drawn from. conditions at a social media marketing
company.
• Your population is all 1000 employees of
• Ideally, it should include the entire the company.
target population (and nobody who • Your sampling frame is the company’s HR
is not part of that population). database, which lists the names and
contact details of every employee.
2/7/2025 54

Population and Sampling Methods

Sample size Probability sampling methods
• The number of individuals you • Probability sampling means that every
should include in your sample member of the population has a chance
depends on various factors, of being selected.
including the size and variability of
the population and your research • It is mainly used in quantitative
design. research.

• There are different sample size • If you want to produce results that are
calculators and formulas depending representative of the whole population,
probability sampling techniques are the
on what you want to achieve with
most valid choice.
statistical analysis.
2/7/2025 55

Population and Sampling Methods

2/7/2025 56

Population and Sampling Methods

• Non-probability sampling methods
• In a non-probability sample, individuals are selected based on non-random
criteria, and not every individual has a chance of being included.
2/7/2025 57

Population and Sampling Methods

2/7/2025 58

Methods for collecting data

Research methods Methods for collecting data

• are specific procedures for collecting • Data is the information that you
and analyzing data. collect for the purposes of
• Developing your research methods is answering your research question.
an integral part of your research
design. • The type of data you need depends
• When planning your methods, there on the aims of your research.
are two key decisions you will make.
2/7/2025 59

Methods for collecting data

Qualitative vs. quantitative data Qualitative vs. quantitative data

• Your choice of qualitative or

quantitative data collection depends on
the type of knowledge you want to
develop.
• If you want to develop a more
mechanistic understanding of a topic, or
• For questions about ideas, experiences your research involves hypothesis testing,
and meanings, or to study something collect quantitative data.
that can’t be described numerically,
collect qualitative data.
2/7/2025 60

Pros Cons
• Flexible – you can often adjust your • Can’t be analyzed statistically,
methods as you go to develop new and not generalizable to broad
knowledge. populations.
• Can be conducted with small samples. • Difficult to standardize researc
at higher risk for research bias
Qualitative
• Can be used to systematically describe • Requires statistical training to
Quantitative
large collections of things. analyze data.
• Generates reproducible
knowledge(Information or insights • Requires larger samples.
derived from research or data analysis
that can be independently verified or
replicated by others)
2/7/2025 61

Quantitative data collection methods Qualitative data collection methods

• Surveys: List of closed or multiple • Interviews: Asking open-ended

choice questions that is distributed to a questions verbally to respondents.
sample (online, in person, or over the • Focus groups: Discussion among a
phone). group of people about a topic to gather
opinions that can be used for further
• Experiments: Situation in which
research.
different types of variables are
• Ethnography: Participating in a
controlled and manipulated to establish
community or organization for an
cause-and-effect relationships. extended period of time to closely
• Observations: Observing subjects in a observe culture and behavior.
natural environment where variables • Literature review: Survey of published
can’t be controlled. works by other authors.
2/7/2025 62

Methods for collecting data

Primary vs. secondary research

• Primary research is any original data • If you are exploring a novel research
that you collect yourself for the question, you’ll probably need to
purposes of answering your research collect primary data.
question (e.g. through surveys,
observations and experiments).
• But if you want to synthesize
• Secondary research is data that has existing knowledge, analyze
already been collected by other historical trends, or identify patterns
researchers (e.g. in a government on a large scale, secondary data
census or previous scientific studies). might be a better choice.
2/7/2025 63

Pros Cons

. Can be collected to answer your  More expensive and

specific research question. time-consuming to
Primary  You have control over the sampling and collect.
measurement methods.  Requires training in dat
collection methods.

 Easier and faster to access.  No control over how dat

Secondary  You can collect data that spans longer was generated.
timescales and broader geographical  Requires extra processin
locations. to make sure it works fo
your analysis.
2/7/2025 64

Methods for collecting data

Descriptive vs. experimental data Descriptive vs. experimental data

• In descriptive research, you collect
data about your study subject • To conduct an experiment, you need
without intervening. The validity of to be able to vary your independent
your research will depend on variable, precisely measure your
your sampling method. dependent variable, and control
for confounding variables.
• In experimental research, you
systematically intervene in a process • If it’s practically and ethically
and measure the outcome. The possible, this method is the best
validity of your research will depend choice for answering questions
on your experimental design. about cause and effect.
2/7/2025 65

Pros Cons
. • Allows you to describe your • No control
research subject without over confounding variabl
Descriptive influencing it. • Can’t establish causality.
• Accessible – you can gather
more data on a larger scale.

• More control over • You might influence your

Experimental confounding variables. research subject in
• Can establish causality. unexpected ways.
• Usually requires more
expertise and resources t
collect data.
2/7/2025 66

What is a Data Collection Tool? Questionnaires

Interview
• This is the process of collecting data through an
• An interview is a face-to-face instrument consisting of a series of questions and
conversation between two prompts to receive a response from the individuals it
individuals with the sole purpose administered to. Questionnaires are designed to coll
data from a group.
of collecting relevant information
to satisfy a research purpose. • For clarity, it is important to note that a questionnai
isn’t a survey, rather it forms a part of it. A survey is
process of data gathering involving a variety of data
• Interviews are of different types collection methods, including a questionnaire.
namely; Structured, Semi-
• On a questionnaire, there are three kinds of question
structured, and unstructured with used. They are; fixed-alternative, scale, and open-
each having a slight variation from ended. With each of the questions tailored to the
nature and scope of the research.
the other.
2/7/2025 67

Observation Focus Groups

This is a data collection method by • The opposite of quantitative research
which information on a phenomenon is which involves numerical-based data,
gathered through observation. this data collection method focuses
more on qualitative research.
The nature of the observation could be
• It falls under the primary category of
accomplished either as a complete
data based on the feelings and
observer, an observer as a participant,
opinions of the respondents.
a participant as an observer, or as a
complete participant.
• This research involves asking open-
ended questions to a group of
This method is a key base for individuals usually ranging from 6-10
ormulating a hypothesis. people, to provide feedback.
2/7/2025 68

e quality of your Research Reliability v validity

Reliability Validity
What does it tell The extent to which the results can be The extent to which the results really
you? reproduced when the research is measure what they are supposed to
repeated under the same conditions. measure.

How is it By checking the consistency of results By checking how well the results
assessed? across time, across different correspond to established theories
observers, and across parts of the and other measures of the same
test itself. concept.
How do they
relate? A reliable measurement is not always A valid measurement is generally
valid: the results might reliable: if a test produces accurate
be reproducible, but they’re not results, they should be reproducible.
necessarily correct.
2/7/2025 69

Type of What does it assess? Example

reliability
The consistency of a measure across time: A group of participants com
do you get the same results when you a questionnaire designed to measure person
repeat the measurement? traits. If they repeat the questionnaire days, w
st-retest reliability or months apart and give the same answers
indicates high test-retest reliab

The consistency of a measure across Based on an assessment criteria checklist

raters or observers: do you get the same examiners submit substantially different re
nterrater reliability results when different people conduct the for the same student project. This indicates
same measurement? the assessment checklist has low inter-
reliab

nternal consistency The consistency of the measurement You design a questionnaire to measure
itself: do you get the same results from esteem. If you randomly split the results into
different parts of a test that are designed halves, there should be a st
to measure the same thing? correlation between the two sets of re
2/7/2025 70

of validity What does it assess? Example

The adherence of a measure A self-esteem questionnaire could be assessed by measuri

truct validity to existing theory and other traits known or assumed to be related to the concep
knowledge of the concept being self-esteem (such as social skills and optimism). Strong
measured. correlation between the scores for self-esteem and associa
traits would indicate high construct validity.

The extent to which the A test that aims to measure a class of students’ level of
ent validity measurement covers all Spanish contains reading, writing and speaking component
aspects of the concept being but no listening component. Experts agree that listening
measured. comprehension is an essential aspect of language ability, so
the test lacks content validity for measuring the overall lev
of ability in Spanish.

rion validity The extent to which the result of A survey is conducted to measure the political opinions of
a measure corresponds to other voters in a region. If the results accurately predict the later
valid measures of the same outcome of an election in that region, this indicates that th
concept. survey has high criterion validity.
2/7/2025 71

Methods for analyzing data

Qualitative analysis methods
• Qualitative analysis is used to understand words, ideas,
• Your data analysis methods will depend on experiences. You can use it to interpret data that was
the type of data you collect and how you collected:
prepare it for analysis.
• From open-ended surveys and interviews, literature revi

• Data can often be analyzed both case studies, ethnographies, and other sources that use
quantitatively and qualitatively. rather than numbers. Using non-probability sampling
methods.

• For example, survey responses could be

• Qualitative analysis tends to be quite flexible and relies
analyzed qualitatively by studying the
the researcher’s judgments, so you have to reflect caref
meanings of responses or quantitatively by
on your choices and assumptions and be careful to avoi
studying the frequencies of responses. research bias.
2/7/2025 72

The “Big 6” Qualitative Analysis Methods

The “Big 6”…. #1: Qualitative Content Analysis
• Is used to evaluate patterns within a piece of
content (for example, words, phrases or images
• Content analysis across multiple pieces of content or sources of
communication. For example, a collection of
• Narrative analysis newspaper articles or political speeches.
• Discourse analysis
• With CA, you could, for instance, identify the
• Thematic analysis frequency with which an idea is shared or spok
• Grounded theory (GT) about – like the number of times a PM-ABIY
AMED is mentioned on Twitter.
• Interpretive phenomenological analysis
(IPA) • Or you could identify patterns of deeper
underlying interpretations – for instance, by
identifying phrases or words in tourist pamphle
that highlight ETHIOPIA as an ancient country
2/7/2025 73

#2: Narrative Analysis #2: Narrative Analysis

As the name suggests, narrative analysis is • For instance, the narrative of a prisoner trying to
all about listening to justify their crime could provide insight into
their view of the world and the justice system.
people telling stories and analyzing what
that means.
• Similarly, analyzing the ways entrepreneurs talk
Since stories serve a functional purpose of about the struggles in their careers or cancer
helping us make sense of the world, we can patients telling stories of hope could
gain insights into the ways that people deal provide powerful insights into their mindsets
with and make sense of reality by analyzing and perspectives.
their stories and the ways they’re told.
• Simply put, narrative analysis is about paying
You could, for example, use narrative
attention to the stories that people tell – and mo
analysis to explore whether how something importantly, the way they tell them.
is being said is important.
2/7/2025 74

#3: Discourse Analysis #3: Discourse Analysis

Discourse is simply a fancy word for written or • To truly understand these conversations or
spoken language or debate. So, discourse speeches, the culture and history of those
analysis is all about analyzing language within involved in the communication are important
its social context. factors to consider.

In other words, analyzing language – such as a • For example, a janitor might speak
conversation, a speech, etc. – within more casually with a CEO in a company that
the culture and society it takes place. emphasizes equality among workers.

For example, you could analyze how a janitor • Similarly, a politician might speak more about
speaks to a CEO, or how politicians speak about terrorism if there was a recent terrorist inciden
terrorism. in the country.
2/7/2025 75

#4: Thematic Analysis

• Thematic analysis looks at patterns of • Let’s take a look at an example.

meaning in a data set – for example, a set
of interviews or focus group transcripts. • With thematic analysis, you could analyze 100
online reviews of a popular sushi restaurant to find
out what patrons think about the place.
• But what exactly does that mean? Well, a • By reviewing the data, you would then identify the
themes that crop up repeatedly within the data –
thematic analysis takes bodies of data for example, “fresh ingredients” or “friendly wait
(which are often quite large) staff”.
and groups them according • So, as you can see, thematic analysis can be pretty
useful for finding out about people’s experiences,
to similarities – in other words, themes. views, and opinions.
• Therefore, if your research aims and objectives
involve understanding people’s experience or view
• These themes help us make sense of the of something, thematic analysis can be a great
content and derive meaning from it. choice.
2/7/2025 76

#5: Grounded theory (GT)

#5: Grounded theory (GT) • What’s most important with grounded theor
is that you go into the analysis with
an open mind and let the data speak for
GT is a powerful qualitative analysis itself – rather than dragging existing
method where the intention is hypotheses or theories into your analysis.
to create a new theory (or theories)
using the data at hand, through a • In other words, your analysis must develop
series of “tests” and “revisions”. from the ground up (hence the name).
• Let’s look at an example of GT in action.
• Assume you’re interested in developing a
Strictly speaking, GT is more theory about what factors influence
a research design type than an analysis students to watch a YouTube video about
method, but we’ve included it here as qualitative analysis.
t’s often referred to as a method.
2/7/2025 77

#6: Interpretive Phenomenological

IPA
Analysis (IPA)

• Such phenomena may range from

• IPA is designed to help you relatively common events – such as
understand motherhood, or being involved in a car
the personal experiences of a accident – to those which
subject (for example, a person or are extremely rare – for example, someone’s
personal experience in a refugee camp.
group of people) concerning a major
life event, an experience or
• So, IPA is a great choice if your research
a situation.
involves analyzing people’s personal
experiences of something that happened to
• This event or experience is the them.
“phenomenon” that makes up the
“P” in IPA.
2/7/2025 78

Quantitative analysis methods

Simple Description INFERENTIAL STATISTICS

• The data analysis with description or • Inferential statistics enable us to test a

assessment may use: hypothesis and draw conclusions, or

inferences regarding a population throug
• Frequency
extrapolation from our experimental dat
• Percentage sample.
• Mean
• Mode • Our choice of statistical method for
• Median hypothesis testing is based on whether
• Standard deviation the experimental data is normally
distributed, and on the scale of the data.
2/7/2025 79

Parametric and non-

Quantitative analysis methods parametric tests

Parametric and non-

parametric tests • Parametric tests assume a Normal Measurem
data at the Interval or Ratio scales while
nonparametric do not – although they are
• For normally distributed data, subject to sample size requirements .
standard parametric tests such as
the T-test and ANOVA tests are • Nonparametric tests are used for Categorica
typically used, while nonparametric data at the Nominal or Ordinal scales.
tests are appropriate if the data • Parametric tests are generally more powerfu
does not follow the normal than non-parametric tests and are more likel
detect a significant effect when one indeed
distribution.
exists.
2/7/2025 80

arametric tests and analogous

onparametric procedures

:
Paired t-test: Used to compare the means of two samples when each individual in one sample also
appears in the other sample.
Unpaired t-test: Used to compare the means of two samples when each individual in one sample is
independent of every individual in the other sample.
2/7/2025 81

Research methods for analyzing data

search method Qualitative or When to use
quantitative?

Statistical Quantitative To analyze data collected in a statistically valid manner (e.g. from
analysis experiments, surveys, and observations).

Meta-analysis Quantitative To statistically analyze the results of a large collection of studies.

Can only be applied to studies that collected data in a statistically valid
manner.

hematic analysis Qualitative To analyze data collected from interviews, focus groups, or textual sources.
To understand general themes in the data and how they are communicated.

Content analysis Either To analyze large volumes of textual or visual data collected from surveys,
literature reviews, or other sources.
Can be quantitative (i.e. frequencies of words) or qualitative (i.e. meanings o
words).
2/7/2025 82

The End