9376 All Notes
9376 All Notes
9376 All Notes
1. Meaning of Research
Research refers to a systematic investigation or inquiry that aims to discover, interpret, or revise facts,
events, behaviors, or theories. It’s often aimed at solving problems, improving existing processes, or
developing new theories and innovations. In academic settings, research is vital for building a knowledge
base within a particular field.
conclusion.
The key aspect of research is that it’s not random; it follows a structured process involving the collection
of data, interpretation, and logical analysis to arrive at conclusions that are both reliable and valid.
Research may be conducted in a variety of fields—scientific, social, medical, etc.—and can serve as a
basis for future work in these areas.
2. Definitions of Research
Research is defined by various scholars, often focusing on its systematic and logical nature. Some of the
classic definitions might include: Research is a systematic creative work which aims to increase the
knowledge,
including knowledge of man, culture and society and the use of that knowledge and
to implement that to new applications.
ii. Scientific research is a systematic collection and interpretation of data. It is
conducted to identify the process of nature and the properties of world. It is
conducted by public, private and charitable bodies. It can be divided into different
categories of academic and application disciplines. It provides the standard of
evaluating the positioning of academic institutions. However, some researchers do
not find this criterion accurate for judging the institution. According to them the
quality of research does not justify the quality of teaching.
iii. Martyn Shuttle worth defined research as, “In the broadest sense of the word, the
definition of research includes any gathering of data, information and facts for the
advancement of knowledge”
iv. According to Creswell, “Research is a process of steps used to collect and analyze
information to increase our understanding of a topic or issue”. It consists of three
steps: Pose a question, collect data to answer the question, and present an answer to
the questio
1
Redman and Mory: “Research is a systematized effort to gain new knowledge.”
Slesinger and Stephenson: Research is "the manipulation of things, concepts, or symbols for the
purpose of generalizing to extend, correct, or verify knowledge."
These definitions emphasize that research involves inquiry, experimentation, and analysis to expand or
refine human knowledge.
3. Objectives of Research
The primary objectives of research can vary based on the field of study and the specific aims of the
researcher. However, the common objectives include:
4. Motivation in Research
Motivation refers to the reasons why individuals or institutions engage in research. Common motivating
factors include:
2
Intellectual Curiosity: The desire to explore and understand new concepts, phenomena, or
problems.
Problem-Solving: Researchers are often driven by the need to find solutions to pressing
problems, whether they’re societal, scientific, or economic.
Practical Applications: In applied research, the motivation might be to develop products,
technologies, or interventions that benefit society or improve practices.
Recognition: Many researchers are motivated by professional advancement, recognition, or
publication.
Policy-Making: Research is often necessary for informed decision-making, especially in public
policy, where research can guide legislation, reforms, or social initiatives.
Research has distinct characteristics that differentiate it from other forms of inquiry:
Introduction
It is the most vital part of a research. Well-written introduction grabs the interest of
the readers. It gives the idea about the level of analysis being conducted in the
research. Therefore, introduction should not only provide clear understanding of the
topic, but it should also explain how the research can be used to address the problem.
Literature Review
The second characteristic of a research work is a literature review. The main purpose
of literature review in the research is to provide background information about the
research problem and to interpret that knowledge to create relation with the case
study.
Discussion
The discussion section of any type of research is the same. It revolves around
interpreting facts and drawing conclusions from them. The discussion section of
social sciences research papers has two separate parts for facts and result. However in most research
papers the facts and the discussion about their implication are
consist of one part.
Objectives of Discussion
• Briefly reiterate the research problem and subject of analysis used for the case
study.
• Explanation of findings after analyzing the facts in concise and declarative
manner.
• To explain the connection between facts and findings.
• Systematic review of each finding.
• To elaborate any unexpected or major findings by conducting the research.
• Highlight the major findings in first then minor findings.
• Explain the connection of findings with past related studies.
3
• Compare and contrast of new findings and former findings, especially if the
subject of analysis is motivated by past study.
• Focus on mentioning of all possible findings acquired from case study, rather
than only those which prove the hypothesis.
• Explanation of limitation and its insignificance in the case study.
• Pointing unanswered questions or issues which are not answered in the case
study.
• Recommendation and importance of new areas of research problem for future
study.
v. Conclusion
The conclusion section of any research paper summarizes the conclusion in simple
and easy to understand manner. A well written conclusion section includes the major
findings from the research in this part. It is written in plain language to reveal the
connection of the findings for addressing the issue. It also describes how the new
findings are different than the prior findings. The key words used in the other
sections of the research are used to make clear understanding of conclusion. If the
limitation and recommendation parts of the case study are not mentioned in the
discussion, then these parts are included in conclusion. The main objective of
conclusion is to restate the main argument in the light of findings of the case study.
In addition, it also sheds light on the context, background and importance of research
problem. It explains how the design of case study is sufficient to address the issue or
fulfilling the gap in past studies. Moreover, it reiterates the significance of the
4
Accuracy: Data collection and analysis must be as precise and accurate as possible.
Relevance: The research must be relevant to the field and have practical implications or
theoretical significance.
Validity and Reliability: The findings must be valid (they measure what they claim to measure)
and reliable (they provide consistent results over time).
Ethics: Good research adheres to ethical standards, including informed consent, confidentiality,
and responsible reporting of results.
7. Types of Research
Research can be categorized in several ways, depending on the purpose, method, and nature of the
inquiry:
By Purpose:
Basic (Pure) Research: Conducted to increase fundamental knowledge and understanding, often
without immediate practical applications.
Applied Research: Aimed at solving practical problems and applying findings to real-world
situations.
By Nature of Data:
By Approach:
Exploratory Research: Used when the problem is not well understood. It seeks to explore the
issue and gather preliminary data.
Descriptive Research: Aims to describe characteristics of a phenomenon or population, but not
necessarily to explain why something happens.
Explanatory Research: Seeks to explain the relationships between variables and the causes
behind certain outcomes.
Correlational Research: Looks for relationships between variables, though it does not
necessarily establish a cause-and-effect link.
Experimental Research: Involves manipulating one variable to observe its effect on another,
establishing causal relationships.
By Time Dimension:
5
Other Types:
UNIT 2
Systematic and structured: Research follows an organized plan or methodology to achieve its
objectives.
Objective: The research should aim to minimize personal biases and subjective opinions.
Empirical: Research is often based on observation, experiments, or data collection.
Logical: Conclusions must be drawn based on logical and evidence-supported reasoning.
Replicable: Other researchers should be able to reproduce the study and obtain similar results.
Rigorous: Research must be thorough, careful, and comprehensive in its methods and analysis.
These characteristics ensure that research is reliable, valid, and can contribute to existing knowledge.
The criteria for good research build on the characteristics but also include:
Clear objectives: The research problem and goals should be well-defined and specific.
Appropriate methodology: The research design, data collection, and analysis methods should
suit the research problem.
Reproducibility: The study should be able to be repeated by others, ensuring the results are not
coincidental.
Ethical adherence: Researchers must follow ethical guidelines, such as informed consent,
confidentiality, and responsible reporting.
Accurate data and analysis: The data collected should be reliable and the analysis should be
conducted using proper techniques to avoid bias or error.
Contribution to knowledge: Good research should add value to the field, advancing
understanding or offering practical solutions.
6
2.4 What is a Research Problem?
A research problem is a specific issue, contradiction, or gap in knowledge that a researcher seeks to
address or investigate. It could be:
Research problems form the foundation of a study. Without a clear problem, the research lacks focus
and direction.
Formulating the problem is crucial because it directly influences the research design, data collection,
and analysis methods.
Delimitation refers to the process of narrowing or setting boundaries for the research problem. This
step ensures the study is focused, manageable, and specific.
In Qualitative Research: Delimitations may include focusing on specific case studies, time
periods, geographical areas, or certain populations. Since qualitative research often involves in-
depth analysis, the problem should be sufficiently narrowed to allow detailed investigation.
In Quantitative Research: The problem is delimited by specifying measurable variables,
choosing particular experimental conditions, or selecting certain datasets. Quantitative studies
benefit from precise definitions and clear boundaries for testing hypotheses.
7
2.7 Delimitations in a Research Problem
Delimitations define what the study will and will not cover. They set the scope of the research by
outlining:
Delimitations clarify the focus of the research, ensuring that it stays on track and doesn’t become too
broad or unfocused.
Defining a research problem involves clearly articulating the issue that the research aims to address. A
well-defined problem statement should:
Defining the problem is critical because it sets the stage for developing research questions, hypotheses,
and methodology.
The problem statement is a formal description of the issue the research seeks to address. It typically
includes:
1. Context or background: Provides a brief overview of what is known about the issue.
2. The gap or issue: Clearly explains what is missing or unresolved in current knowledge.
3. The significance: Justifies why this problem is important to study.
8
4. Research questions or objectives: Lists the specific questions the research aims to answer.
For example: "Despite significant advances in medical technology, the rates of diabetes have been
steadily increasing in urban populations. There is a lack of understanding regarding the role that diet and
lifestyle changes in urban environments play in this trend. This study aims to examine the impact of
dietary patterns and physical activity on the prevalence of diabetes in urban areas."
A well-written problem statement serves as the foundation for the entire research process.
2.10 Conclusion
The conclusion in this section likely summarizes the key points discussed in relation to the research
problem. It may highlight:
The conclusion ties together the ideas of formulating, delimiting, and defining research problems,
emphasizing their importance in conducting effective research.
UNIT 3
The introduction to a literature review gives a general overview of the topic. It explains why a review of
existing literature is crucial for the research, showing how it informs the research questions,
methodology, and scope of the current study. In this section, you'll:
Here, the goals of the literature review are outlined. These objectives vary depending on the field and
research but generally include:
9
Critically evaluating methodologies, theories, and evidence presented in past studies.
Setting a theoretical foundation for your research.
The core section of your review, this provides an in-depth look at the existing body of knowledge. Here,
you summarize and evaluate major studies relevant to your topic. The review might be structured in
several ways:
In this section, you focus on critically analyzing what is known, areas of consensus, areas of
disagreement, and gaps in the research.
The literature review is essentially a critical evaluation of the scholarly work that exists on a given topic.
Its purpose is to offer a synthesis of these works to provide a clear, organized view of the current state
of knowledge. It is not just a summary but also an interpretation of how each piece of literature
contributes to the field.
It provides a background: Helps to familiarize the researcher with the current knowledge on the
topic.
It avoids duplication: Ensures that the researcher does not repeat studies that have already
been done.
It refines research questions: By understanding what’s already known, researchers can adjust
their research focus to unaddressed areas.
10
It informs methodology: By understanding how previous studies were conducted, researchers
can improve upon those methods or avoid their pitfalls.
To identify gaps in the current research: Highlight areas that have not been sufficiently
explored.
To establish the importance of the research problem: Demonstrate why further investigation is
necessary.
To identify key authors and works: Find the major contributors and landmark studies in the
field.
To assess current methodologies: Evaluate the strengths and weaknesses of the research
approaches that have been taken.
To synthesize information: Organize findings to show how they relate to each other.
Sources of literature are where you gather information for your review. They can be categorized as:
1. Primary Sources:
o These include original research, experiments, studies, or firsthand accounts. Examples:
journal articles, conference papers, dissertations, patents.
2. Secondary Sources:
o These interpret or review primary sources. Examples: review articles, meta-analyses,
books, critical essays.
3. Tertiary Sources:
o These provide overviews or indexes to help locate primary and secondary sources.
Examples: encyclopedias, databases, bibliographies.
A comprehensive literature review draws from all three types of sources to give a well-rounded view.
Summarizes existing research: It pulls together all that is known about the topic.
Establishes the relevance of your work: Shows how your research fits into the existing body of
work.
Identifies gaps: Demonstrates what has not been researched, and why your study is needed.
11
Shows trends and relationships: Highlights key findings, patterns, contradictions, or debates in
the literature.
Informs research methodology: Helps refine the methods you'll use based on what has worked
or failed in past research.
1. Define research questions: Clearly outline what you are trying to find out.
2. Search databases: Use academic databases (like JSTOR, PubMed, etc.) to find relevant articles,
books, and reports.
3. Identify key sources: Focus on studies that are relevant, credible, and have made significant
contributions to the field.
4. Evaluate the literature: Critically assess the quality of the research—its validity, reliability, and
relevance to your study.
5. Synthesize information: Organize the studies in a way that makes sense for your review,
drawing connections and highlighting key themes.
When using a library for your literature review, certain precautions should be observed:
Ensure sources are credible: Avoid using non-peer-reviewed material unless it serves a specific
purpose.
Avoid outdated references: Prioritize recent studies unless older ones are seminal or still
relevant.
Track references carefully: Maintain accurate records to avoid issues with plagiarism or citation
mistakes.
Use reference management tools: Software like Zotero or EndNote can help keep track of
sources and ensure proper citation.
12
Link to your own research: Constantly refer back to how the literature connects with your
research question.
Too much summary, not enough analysis: Simply describing what others have done is not
enough. You need to critically evaluate the literature.
Inconsistent structure: Jumping from one topic to another without clear organization can
confuse the reader.
Ignoring recent research: Ensure that you include up-to-date studies, as research fields evolve.
Not connecting the literature to your research: The literature review should lead the reader to
understand why your research is necessary and what contribution it will make.
A literature review is a comprehensive, systematic analysis and synthesis of existing research, studies,
and academic publications on a particular topic. It provides a critical evaluation of past research and
forms the basis for new research by highlighting trends, gaps, and contradictions in the field.
A literature review is more than a summary; it is a structured and organized critique of scholarly work on
a specific subject. It serves to:
Assess the current state of knowledge by highlighting what is known and what remains
unresolved.
Compare and contrast various studies to establish connections and disparities between them.
Synthesize findings to build a coherent picture of the topic, paving the way for new research.
The literature review sets the foundation for any research by ensuring the researcher is well-versed in
relevant literature, helping to prevent redundancy, and guiding the formulation of new hypotheses.
13
2. Why is the Review of Literature Necessary?
A literature review is a critical component of academic research because it serves several important
functions, which ensure the validity and relevance of your work.
A literature review offers a broad overview of the existing knowledge related to your research topic. It
helps you understand the historical and theoretical foundations of your study, making it easier to frame
your research questions effectively.
By reviewing existing literature, researchers can identify areas that have been underexplored or
questions that remain unresolved. This helps to pinpoint where your research can make a significant
contribution, filling gaps or addressing overlooked issues.
A literature review ensures that you are not repeating previous studies unnecessarily. It helps you
determine if your research question has already been addressed or if further investigation is needed.
Through a critical evaluation of past research, a literature review helps refine your research questions
and improve your methodology. By understanding what has worked well or poorly in previous studies,
you can design a more robust and informed research approach.
The literature review allows researchers to establish a theoretical basis for their study. It connects your
research with established theories, showing how your work fits within the broader academic landscape
and supporting the rationale for your research.
Conducting a thorough literature review shows that you are knowledgeable about your research topic. It
demonstrates that you have engaged with key scholars, debates, and methodologies, lending credibility
and academic rigor to your work.
A well-written literature review can justify the need for your research by demonstrating how your study
addresses important gaps or unresolved questions in the field.
14
3. What are the Objectives of a Literature Review?
The objectives of a literature review help guide the direction and structure of the research, ensuring it
serves its purpose effectively. These objectives can be grouped under specific headings:
One of the primary objectives of a literature review is to compile and condense the key findings from
past research. By summarizing the literature, you provide an overview of the current state of knowledge
on the topic.
Another crucial objective is to identify gaps in the current literature—areas that have not been fully
explored or where there is a lack of consensus. This helps position your research as a necessary addition
to the field.
A literature review critically evaluates the methodologies, theories, and conclusions of previous studies.
This helps to assess the validity, reliability, and rigor of the work done so far.
One objective of a literature review is to establish a theoretical foundation that supports your study.
This includes identifying key theories, models, or concepts that will inform your research design and
help explain your findings.
15
Identifying relevant theories that align with your research question.
Explaining how these theories support your hypothesis or research objectives.
Describing how your research will contribute to or challenge existing theoretical models.
A literature review is essential for showing how your research fits into the existing body of knowledge.
By comparing your research with other studies, you demonstrate the importance of your work and its
potential to advance understanding in the field.
Identifying the most influential researchers and landmark studies in your field is an important part of
any literature review. This not only shows that you are familiar with the key contributors but also helps
to position your work in relation to these seminal studies.
Finally, a literature review often serves as a roadmap for future research. By identifying gaps and
suggesting areas for further exploration, your review helps guide not only your study but also potential
future research by others in the field.
A literature review is a comprehensive and systematic summary, synthesis, and critical evaluation of
existing research and publications on a specific topic. It examines past studies to identify trends, gaps,
and the current state of knowledge in the area of interest, helping to place the current research into
context.
16
Meaning of Literature Review:
A literature review is not just a summary but an organized critique of the body of research on a topic. It
helps identify what is already known and what remains to be explored. The review highlights key
findings, areas of debate, contradictions, and methodological approaches, thus providing a foundation
for new research.
To identify knowledge gaps: It helps the researcher to understand what areas have not been
sufficiently studied.
To avoid duplication: Reviewing previous studies ensures the research topic is original and
doesn’t merely replicate existing work.
To refine research questions: By understanding past research, researchers can fine-tune their
questions to address specific gaps.
To develop a theoretical framework: Literature reviews help build a conceptual foundation for
your study.
To inform research design: By examining previous methodologies, researchers can improve
their approach and avoid past mistakes.
To summarize existing research: Provide an overview of what has already been studied on the
topic.
To identify gaps in the literature: Pinpoint areas that require further investigation.
To clarify key concepts: Define and discuss important terms and ideas that are central to the
research.
To assess current methodologies: Evaluate the research methods used in previous studies and
their effectiveness.
To build a theoretical foundation: Help develop the conceptual basis for your own research by
connecting existing theories and findings.
4. What are the Sources of Literature? Describe the Major Sources in Detail
1. Primary Sources
17
These are original materials or firsthand research that present new data, findings, or ideas. Examples
include:
2. Secondary Sources
These sources summarize or analyze primary sources. They provide a broader perspective by reviewing
or critiquing research. Examples include:
Review articles: Papers that summarize and synthesize the research in a particular area.
Books: Scholarly works that provide an overview or analysis of a topic.
Meta-analyses: Statistical analyses that combine results from different studies to draw broader
conclusions.
3. Tertiary Sources
These are compilations or indexes of primary and secondary sources, useful for locating literature.
Examples include:
Summarizes existing research: Provides a comprehensive overview of what has been published
on a given topic.
Identifies research gaps: Highlights areas that have not been sufficiently studied and need
further exploration.
Establishes the relevance of your study: Shows how your research fits into the broader field of
knowledge.
Informs research methodology: Guides the selection of research methods by highlighting what
has worked or failed in past studies.
Builds a theoretical framework: Helps establish key theories or models that your research will
build upon.
18
Steps to Conduct a Literature Review:
1. Define the research question: Clearly articulate the focus of your study and what you are trying
to understand.
2. Search for relevant literature: Use academic databases (Google Scholar, PubMed, JSTOR) to find
relevant research.
3. Evaluate the sources: Critically assess the credibility, relevance, and quality of the studies you
review.
4. Organize the information: Group the studies based on themes, methodologies, or theories.
5. Synthesize and write: Create a coherent narrative that connects the research findings,
highlighting patterns and gaps.
1. Narrative Review: Provides a comprehensive overview of the topic in a narrative form. It is not
limited to specific methodologies.
2. Systematic Review: Follows a rigorous process to identify, evaluate, and synthesize research on
a well-defined topic, often using specific inclusion and exclusion criteria.
3. Meta-Analysis: Combines quantitative data from multiple studies to derive statistical
conclusions.
4. Theoretical Review: Focuses on reviewing the theoretical frameworks and models used in a
particular field.
5. Scoping Review: Maps the key concepts in the literature and identifies gaps, but doesn’t assess
the quality of the studies.
6. Critical Review: Evaluates and synthesizes the existing research but also offers critique and
insight into future directions.
1. Ensure Credibility: Only use peer-reviewed and authentic sources to maintain the accuracy and
reliability of your research.
2. Avoid Plagiarism: Always cite the original authors and keep proper records of the sources you
use to avoid unintentional plagiarism.
19
Begin with a summary of relevant research, focusing on key findings.
Synthesize the research by discussing how the studies are related to each other, showing trends,
debates, and areas of agreement or disagreement.
3. Critically Evaluate:
Provide a critical analysis of the literature. Discuss strengths, weaknesses, and any biases
present in the studies.
Highlight the limitations of the research methods and suggest how your research can address
these issues.
Show how the literature relates to your research. Highlight how your study will fill gaps or build
on previous work.
Use the literature to justify your research questions and methodology.
A hypothesis is a tentative statement or assumption that can be tested through research and
experimentation. It offers a possible explanation for a phenomenon and is subject to verification or
falsification. Hypotheses guide the research process by establishing a focus and suggesting possible
outcomes.
The nature of a hypothesis lies in its role as a provisional explanation that researchers aim to validate. It
is:
20
4.3 Functions of Hypothesis
Guiding research: It directs the focus of study by establishing the relationships between
variables.
Providing a framework: Hypotheses offer a conceptual framework that outlines what the
research seeks to explore or explain.
Facilitating decision-making: In experiments, a hypothesis helps determine the types of data
needed and the methods of data collection.
Predicting outcomes: It allows researchers to anticipate possible results, leading to meaningful
interpretations.
Clarifies research objectives: It defines the specific problem being investigated, avoiding
ambiguity in the research process.
Enhances precision: By proposing a relationship between variables, it fosters a clear
understanding of the focus of the study.
Promotes structured inquiry: Research becomes more systematic when guided by a hypothesis,
leading to efficient resource usage.
Contributes to knowledge: Validating or refuting a hypothesis adds to the body of scientific
knowledge and theory.
There are different types of hypotheses depending on the nature of the research:
1. Null Hypothesis (H0): It states that there is no significant difference or relationship between
variables. It serves as a basis for comparison and is tested for possible rejection.
2. Alternative Hypothesis (H1): This is the hypothesis that suggests a significant effect or
relationship between variables, opposite to the null hypothesis.
3. Directional Hypothesis: It predicts the specific direction of the relationship between variables
(e.g., an increase in variable A leads to an increase in variable B).
4. Non-Directional Hypothesis: It suggests a relationship between variables without specifying the
direction of the effect.
5. Simple Hypothesis: Involves a direct relationship between two variables (one independent and
one dependent).
6. Complex Hypothesis: Involves more than two variables and examines multiple relationships at
once.
21
o This is a straightforward statement where increased study time (independent variable)
is expected to result in higher exam scores (dependent variable).
2. Null Hypothesis: "There is no significant relationship between caffeine consumption and
reaction time."
o This implies that any difference in reaction times is purely by chance or due to random
variability.
3. Alternative Hypothesis: "Consuming caffeine significantly improves reaction time."
o This suggests that caffeine has a measurable effect on improving reaction time.
4. Directional Hypothesis: "Children who eat breakfast will perform better in school than those
who do not."
o Here, the direction is specified, predicting better school performance for children who
have breakfast.
5. Non-Directional Hypothesis: "There is a relationship between exercise frequency and mental
health."
o It does not predict whether increased exercise improves or worsens mental health, only
that a relationship exists.
These hypotheses form the foundation for experimental design, data collection, and analysis, making
them crucial for validating research findings.
A good hypothesis has several essential characteristics that make it effective in guiding research. These
include:
The variables and relationships proposed by the hypothesis must be measurable or perceivable
in real-world settings.
22
Hypotheses based on observable facts are more likely to lead to verifiable outcomes because
they rely on evidence that can be seen, measured, or experienced.
Being grounded in observable things allows researchers to collect data and test the hypothesis
empirically.
It should directly address the issue being investigated and provide a potential explanation or
prediction.
The hypothesis should not introduce unrelated variables or address topics outside the scope of
the study.
Relevance ensures that the hypothesis contributes meaningfully to solving the research problem
or advancing understanding of the topic.
Variables and concepts are both key elements in research, but they are distinct in nature:
Concept: An abstract idea or general notion that represents a phenomenon. Examples include
"intelligence," "satisfaction," or "freedom."
o Concepts are not directly measurable but provide the foundation for defining variables.
Variable: A specific and measurable representation of a concept. For example, "intelligence"
(concept) can be measured as IQ scores (variable), or "satisfaction" (concept) might be
measured using a satisfaction survey (variable).
o Variables are the operational form of concepts that are used in research to observe and
quantify changes.
An independent variable (IV) is the variable that the researcher manipulates or changes to observe its
effect on another variable (the dependent variable). It is the cause or input in an experiment.
The dependent variable (DV) is the variable that is affected or influenced by the independent variable. It
is the outcome or effect being measured in an experiment.
23
Changes in the dependent variable are observed and measured to determine the impact of the
independent variable.
Example: In the same experiment on sleep and memory, memory performance (dependent
variable) is what the researcher measures to assess the effect of varying sleep levels
(independent variable).
An extraneous variable is any variable other than the independent variable that might affect the
outcome (dependent variable) of the experiment. If not controlled, extraneous variables can introduce
bias or error.
Extraneous variables are unwanted variables that might interfere with the relationship between
the independent and dependent variables.
Example: In a study on sleep and memory, factors like caffeine intake or stress levels can act as
extraneous variables that influence memory performance, even though they are not part of the
study’s focus.
Researchers attempt to control extraneous variables to ensure the results accurately reflect the effect of
the independent variable.
An intervening variable (also called a mediator variable) is one that explains the relationship between
the independent and dependent variables. It is not directly observable but helps clarify the underlying
process linking the two.
Intervening variables mediate the effect of the independent variable on the dependent variable.
Example: In a study on the effect of income (independent variable) on happiness (dependent
variable), job satisfaction could be an intervening variable. Higher income may lead to greater
job satisfaction, which in turn results in increased happiness.
Understanding intervening variables helps provide a more comprehensive explanation of how or why
certain relationships occur in research.
A moderator variable is a variable that influences the strength or direction of the relationship between
the independent and dependent variables. Unlike an intervening variable, which explains how or why a
relationship occurs, a moderator affects when or under what conditions the relationship occurs.
A moderator can either strengthen, weaken, or reverse the relationship between two variables.
Example: In a study exploring the relationship between stress (independent variable) and job
performance (dependent variable), social support could act as a moderator. High levels of social
support may weaken the negative impact of stress on job performance.
24
Testing a hypothesis involves assessing whether the hypothesis is supported or rejected based on
empirical data. Researchers design experiments, collect data, and apply statistical methods to test their
hypothesis.
Hypothesis testing helps determine if the observed data fits the predicted relationship or if it
occurs by chance.
After testing, researchers either:
o Reject the null hypothesis (H₀) if there is enough evidence to support the alternative
hypothesis (H₁), or
o Fail to reject the null hypothesis if the evidence is insufficient.
1. Formulation of Hypotheses:
o Develop a null hypothesis (H₀) and an alternative hypothesis (H₁). The null hypothesis
usually states that there is no effect or relationship, while the alternative hypothesis
suggests there is a significant effect.
2. Choosing a Significance Level (α):
o Select a significance level (commonly 0.05) which represents the probability of rejecting
the null hypothesis when it is true (Type I error).
3. Data Collection and Analysis:
o Conduct the experiment or study to collect data and analyze the data using statistical
methods (e.g., t-tests, ANOVA, regression analysis).
4. Conclusion:
o Based on the analysis, decide whether to reject or fail to reject the null hypothesis. If the
p-value is less than the significance level (α), reject the null hypothesis.
25
4.19 Steps to Developing a Hypothesis
1. Identifying the research problem: Start with a specific, researchable question based on the
problem.
2. Reviewing existing literature: Study prior research to find gaps and frame the hypothesis.
3. Defining variables: Clearly identify the independent, dependent, and any potential extraneous
variables.
4. Formulating the hypothesis: Write a clear, testable statement that reflects the expected
relationship between variables.
5. Refining the hypothesis: Ensure that it is concise, testable, and relevant to the research
problem.
1. Clarity and specificity: The hypothesis should be unambiguous and focused on specific variables
and relationships.
2. Testability and measurability: The hypothesis must be testable through empirical data
collection and analysis.
3. Falsifiability: It should be possible to disprove the hypothesis with contrary evidence.
4. Consistency with existing knowledge: The hypothesis should align with prior research and
theoretical frameworks.
5. Relevance: It must address the research problem and contribute to answering the research
question.
A data analysis plan outlines how data will be analyzed after it has been collected. It includes:
1. Data Preparation: Checking for data quality, removing outliers, and dealing with missing data.
2. Choosing the Right Statistical Tests: Based on the type of data and hypothesis, select the
appropriate statistical methods (e.g., correlation analysis, t-tests, regression).
3. Descriptive Statistics: Summarize the data using measures like mean, median, mode, and
standard deviation.
4. Inferential Statistics: Apply tests to draw conclusions about the population from the sample
data (e.g., hypothesis testing, confidence intervals).
5. Data Visualization: Use graphs, charts, and tables to visualize trends, distributions, and
relationships.
6. Interpretation: After analysis, interpret the results in the context of the research question and
hypothesis.
26
1. Alpha (α):
o Represents the significance level of a hypothesis test. It is the probability of committing
a Type I error, which is rejecting the null hypothesis when it is true.
o Commonly set at 0.05, meaning there is a 5% risk of rejecting a true null hypothesis.
o Example: If α = 0.05, the researcher accepts a 5% chance of making a false positive
error.
2. Beta (β):
o Represents the probability of committing a Type II error, which is failing to reject the
null hypothesis when it is false.
o Power of the test is defined as 1 - β, which is the probability of correctly rejecting a false
null hypothesis.
o A lower β (higher power) increases the likelihood of detecting a true effect when one
exists.
o Example: If β = 0.20, there is a 20% chance of not detecting a significant difference when
one actually exists (false negative).
The execution of data analysis refers to the process of applying statistical or analytical techniques to
raw data to draw meaningful insights. This process typically involves the following steps:
1. Data Cleaning: Remove errors, missing values, and inconsistencies to ensure the data is ready
for analysis.
2. Data Exploration: Perform exploratory data analysis (EDA) to get a sense of the data. This may
involve summarizing key variables, visualizing distributions, and identifying patterns or outliers.
3. Selection of Analytical Techniques: Based on the research question and hypothesis, select the
appropriate analysis methods (e.g., regression analysis, ANOVA, chi-square tests).
4. Data Analysis: Apply statistical tests or algorithms to examine relationships between variables,
test hypotheses, or make predictions.
5. Interpretation of Results: Once the analysis is complete, interpret the outcomes in the context
of the research objectives. This involves considering the significance of the results, potential
limitations, and their broader implications.
6. Reporting: Present the findings using charts, graphs, or tables, along with a written explanation
of the results.
There are several types of data analysis, depending on the research goals and the nature of the data:
1. Descriptive Analysis:
o Involves summarizing the basic features of the data, such as means, medians, modes,
and standard deviations.
o Example: Reporting the average income of survey respondents.
2. Inferential Analysis:
27
o Used to make predictions or inferences about a population based on sample data. It
involves hypothesis testing, confidence intervals, and significance testing.
o Example: Conducting a t-test to determine if two groups differ significantly in their exam
scores.
3. Exploratory Data Analysis (EDA):
o Aimed at discovering patterns, relationships, or anomalies in the data without having
specific hypotheses.
o Example: Using scatter plots or correlation matrices to investigate relationships
between variables.
4. Predictive Analysis:
o Uses historical data to make predictions about future outcomes. This often involves
regression models, time-series analysis, and machine learning algorithms.
o Example: Predicting future sales based on historical sales trends.
5. Causal Analysis:
o Examines the cause-and-effect relationships between variables. This typically involves
controlled experiments or statistical techniques like regression to isolate the effects of
the independent variable on the dependent variable.
o Example: Determining whether a new teaching method causes an improvement in
student test scores.
6. Prescriptive Analysis:
o Goes beyond predicting future outcomes by recommending actions to achieve desired
outcomes. This often involves optimization techniques.
o Example: Suggesting marketing strategies based on customer purchasing behavior data.
In the context of data analysis, decision making involves using the insights gained from the analysis to
make informed choices or strategic actions. The process typically includes:
1. Identifying Key Findings: Reviewing the results of the data analysis to identify trends, patterns,
or statistically significant relationships that are relevant to the decision-making process.
2. Evaluating Options: Based on the insights, consider different courses of action and evaluate
their potential outcomes. Use quantitative models, such as decision trees or cost-benefit
analyses, to assess the pros and cons.
3. Risk Assessment: Evaluate the potential risks associated with each decision. This could include
financial risks, operational challenges, or external factors that may affect the decision.
4. Selecting the Best Option: Choose the option that aligns with the organization's goals,
minimizes risk, and maximizes potential benefits. Data-driven decisions help reduce uncertainty
and bias in the decision-making process.
5. Implementation: Once a decision is made, it must be implemented effectively, with a clear plan
of action and monitoring to ensure that the intended results are achieved.
6. Review and Feedback: After implementation, review the decision's impact by measuring key
performance indicators (KPIs). Feedback helps refine future decision-making processes.
28
A conclusion is the final section of a research or analysis process where findings are summarized, the
hypothesis is evaluated, and the overall results are interpreted in the context of the original research
question or objective.
1. Summary of Findings: Recap the main findings from the analysis, highlighting significant results
and trends. This should directly address the research questions or hypotheses posed at the
beginning.
2. Hypothesis Evaluation: Reflect on whether the hypothesis was supported or refuted by the
data. If multiple hypotheses were tested, indicate which ones were confirmed and which were
rejected.
3. Implications of Results: Discuss the broader implications of the findings. What do the results
mean in the context of the research problem? How do they contribute to the existing body of
knowledge or theory? Consider both theoretical and practical implications.
4. Limitations of the Study: Acknowledge any limitations in the study design, data collection, or
analysis that could affect the validity or generalizability of the findings. This could include
sample size, measurement errors, or confounding variables.
5. Recommendations for Future Research: Suggest areas for further research, especially if the
findings were inconclusive or if new questions emerged during the study. This helps guide future
studies that can build on the current research.
6. Final Thoughts: Provide a closing statement that ties the research together and reiterates the
significance of the study. This might include reflections on the study's contribution to the field or
its potential real-world applications.
In conclusion, the analysis not only tests the hypothesis but also provides valuable insights for making
informed decisions and understanding the implications of the results in a broader context
UNIT 5
Variables are measurable traits or characteristics that can take on different values. In research, variables
are classified into different types, depending on their role in the study:
Independent Variables: The variable that is manipulated or controlled to test its effects on the
dependent variable.
Dependent Variables: The outcome variable that is being studied, which is affected by changes
in the independent variable.
Control Variables: Factors that are kept constant to prevent them from influencing the results.
Confounding Variables: External variables that may affect the relationship between the
independent and dependent variables if not controlled.
29
The subject of study refers to the main focus or the population, phenomenon, or issue being
researched. It is the specific aspect of reality that the research aims to explore, analyze, and understand.
To convert a concept into a variable, researchers must define the concept in measurable terms. This
process involves identifying observable or quantifiable indicators that represent the concept.
For example:
Concept: Intelligence
Variable: IQ score (as a measurable form of intelligence)
This allows researchers to empirically test and analyze the concept within a study.
5.4 Operationalization
Operationalization is the process of defining a concept so that it can be measured. It involves specifying
how a concept will be observed and measured in the context of a study.
In detail: This requires identifying clear, objective criteria and methods for measuring variables.
For instance, in a study on "job satisfaction," operationalizing the concept might involve creating
a questionnaire where job satisfaction is measured by specific indicators such as employee
retention, self-reported happiness, and workplace performance.
Quantitative research and qualitative research are two fundamental approaches in social science and
scientific studies. Both approaches have different methods, objectives, and ways of handling data.
Quantitative Research:
Objective: To quantify the problem by collecting numerical data and using statistical methods to
analyze it.
Focus: On the measurement of quantities, amounts, frequencies, or patterns.
Methodology: Often involves large sample sizes, surveys, questionnaires, structured interviews,
experiments, or using secondary numerical data.
Data: Numerical, easily translated into statistics. Data is often collected in measurable variables,
such as height, age, or income.
Outcome: Generalizable results, statistical relationships, or trends. The focus is on answering
"how many," "how much," or "to what extent."
Examples:
A survey of 1,000 people to determine the percentage who favor a particular policy.
Experiments to determine the effect of a drug on recovery time.
30
Qualitative Research:
Objective: To understand the underlying reasons, opinions, and motivations for behaviors or
phenomena.
Focus: On exploring ideas, meanings, and experiences in depth.
Methodology: Often involves smaller sample sizes, in-depth interviews, focus groups, case
studies, participant observation, and open-ended surveys.
Data: Non-numerical (words, images, observations). Data is rich and detailed, often based on
open-ended questions or descriptive analysis.
Outcome: Understanding of patterns, themes, or deeper insights into complex social or human
behaviors. The focus is on answering "why" or "how."
Examples:
Variables can be categorized based on their role in the research, measurement scale, and the way they
influence other variables. Here’s a breakdown:
Independent Variables (IV): Variables that are manipulated or controlled by the researcher to
observe their effect on other variables.
Dependent Variables (DV): Variables that are affected by changes in the independent variable.
They represent the outcomes or effects.
Confounding Variables: These variables are not of primary interest but can affect both the
independent and dependent variables, potentially leading to incorrect conclusions if not
controlled.
Control Variables: Variables that are kept constant throughout the research to eliminate their
influence on the dependent variable.
Discrete Variables: Variables that have distinct, separate values, often representing counts (e.g.,
number of children, number of cars).
Continuous Variables: Variables that can take on any value within a given range, often
representing measurements (e.g., height, weight, temperature).
Nominal Variables: Variables that represent categories without a specific order (e.g., gender,
nationality, hair color).
Ordinal Variables: Variables that represent ordered categories, but the intervals between them
are not necessarily equal (e.g., education level, satisfaction rating).
Interval Variables: Variables where the differences between values are meaningful, but there is
no true zero point (e.g., temperature in Celsius, IQ scores).
31
Ratio Variables: Variables where both differences and ratios between values are meaningful,
and there is a true zero point (e.g., height, weight, age).
Study design is the overall strategy that researchers use to integrate the different components of the
study in a coherent and logical way. It helps ensure that the research problem is addressed effectively.
Let’s go into more detail:
1. Experimental Design:
In experimental research, the researcher manipulates the independent variable to observe its effect on
the dependent variable, often in a controlled environment. This design is considered the most reliable
way to establish causal relationships.
Randomized Controlled Trials (RCT): Participants are randomly assigned to either a treatment
group (receiving the intervention) or a control group (receiving no intervention or a placebo).
Pre-test/Post-test Designs: Measurements are taken before and after an intervention to assess
its effect.
2. Quasi-Experimental Design:
This type of research also aims to identify causal relationships, but lacks random assignment. It is often
used when it is unethical or impractical to randomly assign participants to groups.
Non-equivalent Groups Design: In this design, participants are assigned to groups, but not
randomly. Researchers compare outcomes across these groups.
Interrupted Time Series: Repeated measures are taken before and after an intervention to
detect any changes over time.
3. Correlational Design:
In correlational studies, researchers measure two or more variables to assess the statistical relationship
between them, without manipulating any variables. This type of design can identify associations but
cannot establish causality.
Positive Correlation: As one variable increases, the other variable also increases.
Negative Correlation: As one variable increases, the other decreases.
No Correlation: No relationship exists between the variables.
4. Cross-Sectional Design:
In a cross-sectional study, data is collected at a single point in time from a sample population. This
design is often used in surveys and epidemiological research to assess prevalence and relationships at
one point in time.
32
Example: A survey administered to determine the rate of smartphone use among high school
students on a particular day.
5. Longitudinal Design:
A longitudinal study collects data from the same subjects over a period of time. This allows researchers
to observe changes and developments over time and is useful for studying long-term effects.
Panel Study: The same individuals are surveyed at multiple points in time.
Cohort Study: Follows a group of people who share a common characteristic (e.g., birth year)
over time.
Case studies involve an in-depth examination of an individual case or a small group of cases, providing
detailed insights into complex issues. This is commonly used in qualitative research but can also include
quantitative elements.
7. Comparative Design:
A comparative study examines two or more cases to identify patterns or differences between them. It
can be cross-sectional or longitudinal, depending on the time frame used.
Example: Comparing educational outcomes between public and private school students.
8. Survey Design:
In survey research, standardized questionnaires are used to collect data from a large number of
respondents. Survey designs can be cross-sectional or longitudinal and can include both qualitative and
quantitative questions.
9. Descriptive Design:
33
Summary of the Types of Study Designs
UNIT 6
Data collection is the process of systematically gathering information for a research study. The type of
data you collect and the methods you use depend on the research design and objectives. There are two
main types of data:
1. Primary Data:
This is original data collected by the researcher specifically for their study. Methods for collecting
primary data include:
Surveys and Questionnaires: A structured set of questions to gather data from a large group.
Interviews: In-depth, one-on-one discussions to explore participants' views and experiences.
Observations: Watching subjects in natural or controlled settings to gather behavioral data.
Experiments: Controlled investigations where variables are manipulated to observe outcomes.
2. Secondary Data:
This is data that has already been collected by others for a different purpose, but can be used in your
research. Sources of secondary data include:
Census reports
Administrative data
Academic publications
Company records
The method of data collection should be selected based on the research question, the study population,
and the resources available.
34
6.3 Observation Method
Observation involves watching and recording the behaviors or events of interest. It is often used in
social sciences to study natural behaviors in real-time without interfering with the subjects.
1. Participant Observation: The researcher actively participates in the setting or community being
studied while observing behaviors and interactions. This method is often used in ethnographic
research.
o Example: A researcher living in a community to understand local customs and social
interactions.
2. Non-Participant Observation: The researcher observes from a distance without getting involved
in the activities or environment of the subjects.
o Example: Watching children's play behavior in a playground from afar.
3. Structured Observation: The researcher uses a predefined checklist or coding scheme to record
specific behaviors or events. This is more common in quantitative research.
o Example: Recording how often a teacher gives positive reinforcement in a classroom.
4. Unstructured Observation: The researcher takes open-ended notes on everything observed.
This is often used in exploratory or qualitative research.
o Example: A field study where a researcher notes all social interactions in a marketplace.
Advantages of Observation:
Disadvantages of Observation:
Interviews are a qualitative data collection method that involves asking respondents open-ended or
structured questions. Interviews are effective in exploring deep insights, personal experiences, or
complex behaviors.
Types of Interviews:
1. Structured Interviews:
o The interviewer asks predefined, standardized questions in a specific order.
35
o This type of interview is useful for ensuring consistency across respondents, as each
participant answers the same questions.
o Example: A job interview with a fixed set of questions for all candidates.
2. Semi-Structured Interviews:
o The interviewer follows a guide but has the flexibility to ask follow-up questions based
on the responses.
o This allows for both structure and depth, making it ideal for exploratory research.
o Example: An interview with a healthcare professional discussing patient care but
allowing elaboration on certain topics.
3. Unstructured Interviews:
o The interview is open-ended, with no predefined questions. The conversation flows
based on the participant’s responses.
o This is commonly used in case studies or ethnographies where in-depth insights are
sought.
o Example: A narrative interview exploring the life history of a migrant worker.
4. Focus Group Interviews:
o A small group of participants is interviewed together. The researcher facilitates
discussion on a specific topic, allowing group dynamics to influence responses.
o Example: A focus group discussing consumer preferences for a new product.
Advantages of Interviews:
Disadvantages of Interviews:
Questionnaires are a common and efficient data collection tool, especially in large-scale research. They
consist of a series of questions designed to gather information from respondents about specific topics or
variables.
Types of Questionnaires:
1. Closed-Ended Questionnaires:
o Respondents choose from predefined options (e.g., multiple-choice, yes/no, rating
scales).
o Useful for quantitative data and statistical analysis.
36
o Example: A survey asking respondents to rate their satisfaction with a service on a scale
of 1 to 5.
2. Open-Ended Questionnaires:
o Respondents answer in their own words without restrictions. This format is useful for
qualitative data that seeks to understand opinions, thoughts, and experiences.
o Example: A question asking respondents to describe their feelings about a recent policy
change.
3. Mixed Questionnaires:
o Combine both closed-ended and open-ended questions to collect both quantitative and
qualitative data.
o Example: A survey that asks respondents to rate their experience on a scale and then
provides space to elaborate on their ratings.
Structure of a Questionnaire:
1. Introduction:
o This section explains the purpose of the questionnaire, the importance of the
respondent’s participation, and ensures confidentiality. It also provides instructions on
how to complete the questionnaire.
2. Demographic Questions:
o These questions gather information about the respondent’s background (e.g., age,
gender, education level, income).
3. Main Body:
o Questions related to the specific research objectives. These can be closed-ended (e.g.,
Likert scales, multiple choice) or open-ended (e.g., "What do you think about...?").
o The main questions should be arranged logically, starting from general to more specific
topics.
4. Concluding Section:
o A thank-you message or space for any additional comments.
Advantages of Questionnaires:
Efficient: Can collect data from a large group in a relatively short time.
Standardized: All respondents answer the same questions, which makes comparison easier.
Anonymity: Respondents may feel more comfortable providing honest answers if they are
anonymous.
Disadvantages of Questionnaires:
Lack of depth: Closed-ended questions may not provide rich or detailed data.
Low response rates: Particularly in self-administered questionnaires, there is a risk that many
people may not complete and return the form.
Misunderstandings: Respondents may misinterpret questions without the opportunity to seek
clarification.
37
1. Likert Scale: Respondents indicate their level of agreement or disagreement with a statement
(e.g., "Strongly agree" to "Strongly disagree").
o Example: "I am satisfied with my job: Strongly Agree / Agree / Neutral / Disagree /
Strongly Disagree."
2. Multiple Choice: Respondents choose one or more answers from a list of options.
o Example: "What is your preferred mode of transport? a) Car, b) Bus, c) Bicycle, d) Walk."
3. Rank Order: Respondents rank items according to their preferences.
o Example: "Rank the following factors in order of importance to you: a) Salary, b) Job
security, c) Work-life balance."
4. Open-Ended: Respondents provide answers in their own words.
o Example: "What do you think is the biggest challenge facing the healthcare system
today?"
These methods and tools form the foundation of data collection in research. Each method has
specific strengths and weaknesses that should be carefully considered based on the research
objectives.
Secondary data refers to data that was collected by someone else for a different purpose but is now
being used by a researcher for their own study. It is often more cost-effective and less time-consuming
than collecting primary data. However, it may not always fit perfectly with the research objectives or
questions.
38
2. Academic Publications:
o Books, journal articles, and conference papers often contain useful data, especially for
literature reviews or comparative studies.
o Example: A meta-analysis of previous research studies on climate change.
3. Administrative Data:
o Organizations, schools, hospitals, or businesses generate data during their day-to-day
operations. This can be used for research purposes with permission.
o Example: Hospital patient records used for a study on disease prevalence.
4. Historical Data:
o Historical archives, letters, and past records are often used in research that aims to
analyze past events or trends.
o Example: Historical weather records used in climate studies.
Fit for purpose: The data may not perfectly match the researcher's questions or variables.
Data quality issues: The researcher may have little control over the accuracy, reliability, or bias
in the original data.
Outdated data: Depending on when the data was collected, it might no longer reflect current
conditions.
Features of a Questionnaire:
1. Standardized Format:
o All respondents answer the same set of questions in the same way, making the data
comparable across respondents.
2. Self-administered or Interviewer-administered:
o Questionnaires can be filled out by the respondent themselves (online or paper-based)
or administered by an interviewer in person or over the phone.
3. Types of Questions:
o Closed-ended questions: Provide a fixed set of responses (e.g., multiple-choice, Likert
scales).
39
o Open-ended questions: Allow respondents to answer in their own words, giving more
nuanced responses.
Advantages of Questionnaires:
Disadvantages of Questionnaires:
Response bias: Participants may answer questions in a way they think is socially desirable,
rather than truthfully.
Low response rates: In self-administered questionnaires, particularly online, response rates can
be low.
Inflexibility: The structure of the questionnaire limits the ability to explore new or unexpected
topics in depth.
6.9 Observation
Observation as a research method involves systematically watching and recording behaviors or events
in their natural setting or under controlled conditions. It can be used in both qualitative and quantitative
research and is particularly useful for studying behavior, social interactions, or physical environments.
1. Participant Observation:
o The researcher immerses themselves in the setting they are studying, interacting with
the participants.
o Example: A researcher joining a community event to observe group dynamics.
2. Non-Participant Observation:
o The researcher observes without becoming part of the setting. They remain an outsider
and do not interact with the subjects being studied.
o Example: Observing student behavior in a classroom without interacting with them.
3. Structured Observation:
o The researcher uses a checklist or coding system to systematically record behaviors or
events.
o Example: Recording how many times a teacher praises students during a lesson.
4. Unstructured Observation:
o The researcher observes and records everything, without a predefined checklist or
coding system. This is more exploratory and flexible.
o Example: Observing a cultural ceremony to understand its meaning without
predetermined categories.
40
Key Elements in Observational Research:
Advantages of Observation:
Provides real-time data: Observations occur in real-time, offering immediate insights into
behavior.
Allows for the study of non-verbal behavior: Many social or physical behaviors cannot be
captured through questionnaires or interviews.
Useful for studying social dynamics: Observation allows researchers to understand complex
social behaviors in context.
Disadvantages of Observation:
Observer bias: The researcher's own beliefs or expectations may influence what they observe
and record.
Time-consuming: It requires significant time and effort to observe and record data.
Ethical issues: Observing people without their knowledge may raise ethical concerns, especially
in private settings.
The scales of measurement are critical in understanding how data is quantified, analyzed, and
interpreted in research. They define the nature of the data being collected and determine which
statistical analyses are appropriate. There are four primary scales of measurement:
1. Nominal Scale:
Definition: Categorizes data without any order or ranking. The numbers or names assigned to
categories are merely labels and have no quantitative value.
Example: Gender (male, female, other), hair color (blonde, brunette, black), or types of cars
(sedan, SUV, truck).
Characteristics:
o Data is qualitative (categorical).
o No inherent order or ranking of categories.
o Statistical operations: Mode can be used to identify the most common category.
2. Ordinal Scale:
Definition: Categorizes data with a meaningful order or ranking, but the intervals between the
ranks are not necessarily equal.
Example: Socioeconomic status (low, middle, high), education level (high school, undergraduate,
graduate), or customer satisfaction ratings (satisfied, neutral, dissatisfied).
Characteristics:
41
o Data is qualitative but can be ranked.
o The distance between ranks is unknown or unequal.
o Statistical operations: Median and mode can be used.
3. Interval Scale:
Definition: Measures data on a scale with equal intervals between values, but there is no true
zero point.
Example: Temperature in Celsius or Fahrenheit, IQ scores, or the year (e.g., 1990, 2000, 2010).
Characteristics:
o Data is quantitative.
o Equal intervals between units, but zero does not mean "absence of the variable" (e.g.,
0°C does not mean there is no temperature).
o Statistical operations: Mean, median, mode, and standard deviation can be calculated.
4. Ratio Scale:
Definition: Similar to the interval scale, but with the addition of a true zero point, meaning zero
indicates the absence of the measured variable.
Example: Height, weight, age, distance, or income.
Characteristics:
o Data is quantitative with equal intervals between units and a true zero point.
o Statistical operations: All arithmetic operations, including ratios, can be used (e.g.,
"twice as much" is meaningful).
o This is the most powerful scale for statistical analysis.
The scale of measurement affects the type of statistical analysis you can perform.
For example, nominal and ordinal scales use non-parametric statistics, while interval and ratio
scales allow for more sophisticated parametric tests.
In research, measurement tests are used to assess the reliability and validity of the instruments or
scales used for data collection. Ensuring that a measurement tool accurately and consistently measures
what it is intended to measure is crucial for the credibility of the research.
1. Reliability Tests:
o Definition: Reliability refers to the consistency or repeatability of a measurement.
o Types of Reliability:
Test-retest reliability: Measures the stability of a test over time by
administering the same test to the same group at two different times.
42
Inter-rater reliability: Assesses the consistency of measurements when
different observers or raters assess the same phenomenon.
Internal consistency: Measures how well different items on a test measure the
same construct (e.g., using Cronbach’s alpha).
2. Validity Tests:
o Definition: Validity refers to the extent to which a test measures what it is intended to
measure.
o Types of Validity:
Content validity: Ensures the test fully represents the construct being measured
(e.g., a math test covering all relevant topics, not just one area).
Construct validity: Tests whether the instrument measures the theoretical
construct it is intended to measure (e.g., whether a depression scale accurately
measures symptoms of depression).
Criterion-related validity: Assesses whether a test correlates with an outcome
or criterion. This can be further divided into:
Predictive validity: The extent to which the test predicts future
outcomes.
Concurrent validity: The extent to which the test correlates with other
measures taken at the same time.
3. Factor Analysis:
o Definition: A statistical method used to understand the structure of a set of variables or
the underlying relationships between them. Factor analysis is often used to validate
questionnaires by identifying patterns in the responses and grouping related items
together.
4. Standardization:
o Definition: This involves administering the test under consistent conditions to ensure
that any differences in results are due to the test itself and not external factors.
Standardized tests have norms that allow for comparison across different groups.
If a test is reliable, it produces consistent results over time or across different observers.
If a test is valid, it accurately measures the concept or variable of interest.
A reliable test is not necessarily valid (it can be consistent but not measure the intended
concept), but a valid test must be reliable.
Document analysis is a qualitative research method that involves the systematic examination and
interpretation of documents to gain an understanding of the topic or phenomenon being studied. It is
often used in historical research, case studies, and content analysis.
1. Public Records:
43
o Official government reports, organizational records, legal documents, policy papers, and
other publicly available documents.
o Example: Census reports, public health guidelines, or government policy documents.
2. Personal Documents:
o Diaries, letters, emails, autobiographies, and other personal writings that provide
insights into individual experiences and perspectives.
o Example: Letters from a soldier during wartime to understand their personal
experience.
3. Mass Media:
o Newspapers, magazines, advertisements, social media content, and other forms of
media that reflect public opinion or societal trends.
o Example: Analyzing news articles to study media representation of a particular social
issue.
4. Archival Records:
o Historical documents such as manuscripts, photographs, and meeting minutes stored in
archives.
o Example: Analyzing old business meeting records to study organizational changes over
time.
1. Identifying Documents:
o Select documents that are relevant to your research question or topic. The documents
may be written, visual, or digital.
2. Evaluating Authenticity and Credibility:
o Ensure that the documents are authentic (genuine) and credible (trustworthy).
o Questions to consider: Who created the document? For what purpose? When was it
created, and how accurate is it?
3. Analyzing Content:
o Use a structured approach to extract themes, concepts, or patterns from the
documents.
o This often involves coding, categorizing, and interpreting data in relation to the research
objectives.
4. Cross-checking with Other Data:
o Use document analysis in combination with other methods (like interviews or
observations) to triangulate findings and increase the reliability of the research.
Availability: Documents are often readily available, making them a convenient source of data.
Non-intrusive: Unlike interviews or surveys, document analysis does not interfere with the
subject.
Historical insight: Provides access to past events or trends that cannot be studied through other
methods.
Bias: Documents can reflect the bias of the author or organization that created them.
44
Incomplete data: Documents may not contain all the information needed for a comprehensive
analysis.
Interpretation issues: The meaning of the document can be subjective and vary based on the
researcher's perspective.
These methods and scales of measurement play crucial roles in ensuring that the data collected is
accurate, reliable, and fit for analysis. Let me know if you'd like to dive deeper into any of these areas!
UNIT 7
Research philosophy refers to the underlying beliefs and assumptions that guide how research is
conducted, what constitutes knowledge, and how this knowledge is obtained. It shapes the research
approach, methodology, and the interpretation of results.
1. Ontology:
o Definition: The study of what exists; the nature of reality.
o Key Questions: What is the nature of the social world? Is reality objective and external
to the observer, or is it subjective and shaped by human perceptions?
o Two Main Views:
Realism: Reality exists independently of human thoughts and beliefs.
Relativism: Reality is constructed through social processes and perceptions.
2. Epistemology:
o Definition: The study of knowledge; how we come to know things.
o Key Questions: What counts as knowledge? How is knowledge acquired, and what is
considered valid?
o Two Main Views:
Positivism: Knowledge is obtained through observable and measurable facts,
often through scientific methods.
Interpretivism: Knowledge is gained through understanding human
experiences, social contexts, and interpretations.
3. Axiology:
o Definition: The study of values and ethics in research.
o Key Questions: What is the role of the researcher's values in the research process?
Should research be value-free, or do researchers’ biases and values influence the
results?
4. Methodology:
o Definition: The approach or strategy used to gather, analyze, and interpret data.
o Key Questions: What methods are appropriate for gathering data? Should research be
quantitative, qualitative, or mixed methods?
45
Helps researchers understand the nature of their research and its limitations.
Guides the choice of methodology and techniques used in research.
Influences the interpretation of results and the type of conclusions drawn.
The Research Onion, developed by Saunders et al. (2007), is a visual model that describes the stages a
researcher must go through when developing a research methodology. Research philosophy forms the
outermost layer, reflecting its foundational role in guiding the entire research process.
1. Philosophies:
o This layer includes philosophical approaches such as positivism, interpretivism, realism,
and pragmatism. These philosophies guide how the researcher approaches the nature
of reality and knowledge.
2. Approaches:
o Refers to deductive (testing theories) or inductive (developing theories from
observations) approaches to research.
3. Strategies:
o Choices like experiments, surveys, case studies, and ethnography that determine how
data will be collected and analyzed.
4. Choices:
o Refers to the use of mono-methods (only qualitative or quantitative), mixed methods,
or multi-methods approaches.
5. Time Horizons:
o Deciding whether the research will take place over a single time period (cross-sectional)
or over an extended period (longitudinal).
6. Techniques and Procedures:
o The final layer that details specific data collection and analysis techniques (e.g.,
interviews, observations, statistical tools).
Research philosophy is at the core of determining how researchers perceive their research
questions, what methods they will use, and how they interpret their findings.
It frames the entire research process, providing a foundation for more practical decisions in
subsequent layers of the Research Onion.
46
Selecting a research philosophy depends on the nature of the research question, the goals of the
research, and the type of data being collected. Different philosophies offer different perspectives on
how knowledge is understood and produced.
1. Positivism:
o Focus: Objective reality that can be observed and measured.
o Methods: Emphasizes quantitative methods, such as experiments and surveys, that can
yield statistical results.
o Example: A positivist study on the impact of advertising on consumer behavior might
use statistical data to measure changes in sales after an ad campaign.
2. Interpretivism:
o Focus: Understanding the subjective meanings and interpretations individuals give to
social phenomena.
o Methods: Emphasizes qualitative methods, such as interviews and ethnography, that
explore lived experiences.
o Example: An interpretivist study on consumer behavior might involve in-depth
interviews to understand how individuals perceive advertisements.
3. Realism:
o Focus: Reality is independent but can be interpreted differently based on social
conditioning.
o Methods: Combines both qualitative and quantitative methods to provide a fuller
understanding of phenomena.
o Example: A study on public health that uses both statistical data on disease prevalence
and interviews to understand patients' experiences.
4. Pragmatism:
o Focus: The research approach depends on the research question. Knowledge is viewed
in practical terms.
o Methods: Uses a combination of methods (mixed methods) based on what works best
for answering the research question.
o Example: A study on education might use surveys to gather quantitative data on student
performance and interviews to explore teachers’ perspectives.
Study design refers to the framework or plan used to answer research questions. It involves specifying
how data will be collected, what data will be collected, and how it will be analyzed. Study design is
heavily influenced by the chosen research philosophy and can be broadly categorized into qualitative,
quantitative, or mixed methods.
1. Descriptive Research:
47
o Aims to describe characteristics or phenomena. It answers the "what" questions,
providing an understanding of current conditions.
o Example: A survey describing the demographic characteristics of a population.
2. Exploratory Research:
o Used to explore a phenomenon or issue without clear hypotheses at the outset. It often
uses qualitative methods.
o Example: Exploring the reasons behind a rise in social media usage through focus
groups.
3. Explanatory Research:
o Seeks to explain why or how something occurs by identifying cause-and-effect
relationships.
o Example: An experiment examining how different teaching methods affect student
performance.
4. Correlational Research:
o Aims to determine the relationship between two or more variables, without establishing
causality.
o Example: Studying the correlation between exercise habits and academic performance.
5. Experimental Research:
o Involves manipulating variables to test hypotheses and identify causal relationships.
o Example: A randomized controlled trial testing the effectiveness of a new drug on
disease outcomes.
Quantitative research focuses on collecting and analyzing numerical data to quantify variables and find
patterns, relationships, or trends. It is often associated with a positivist research philosophy and uses
deductive reasoning.
Objective: Focuses on measurable facts and uses statistical techniques to analyze data.
Structured: Uses structured tools, such as surveys and experiments, to collect data.
Large sample sizes: Often involves large samples to ensure the generalizability of results.
Surveys: Use questionnaires or structured interviews to collect data from a large group.
Experiments: Involve manipulation of variables to observe effects.
Statistical analysis: Uses statistical tools to analyze relationships between variables.
48
Qualitative research aims to understand human experiences, social contexts, and subjective meanings.
It often involves in-depth exploration and is aligned with interpretivist or constructivist research
philosophies.
These sections are essential in understanding how the philosophy of research influences every step of
the research process, from the study design to the methods employed
Key Characteristics:
Strengths:
Limitations:
49
7.10 Explanatory Study Design of Research
An explanatory study design seeks to explain the relationships or causes underlying a phenomenon. It
goes beyond describing phenomena by establishing causal links between variables.
Key Characteristics:
Strengths:
Limitations:
An exploratory study design is used when little is known about a phenomenon. Its primary goal is to
investigate a research problem or develop hypotheses without a rigid framework, allowing for flexibility
and open-ended inquiry.
Key Characteristics:
Objective: To explore new areas of research where there is little or no prior knowledge.
Methods: Qualitative methods like interviews, focus groups, and ethnography are commonly
used. Researchers often collect data without predefined hypotheses.
Example: A study exploring the experiences of remote workers during the COVID-19 pandemic
to identify common challenges.
Strengths:
Flexible and adaptable to new information that emerges during the study.
Helps identify new research questions and variables for future studies.
Limitations:
50
Cannot provide definitive answers or establish causality.
Results are often preliminary and require further testing in subsequent research.
Correlational research investigates the relationships between two or more variables to determine
whether they are related. However, it does not establish causality—only the strength and direction of
the relationship.
Key Characteristics:
Objective: To determine whether a relationship exists between variables and how strong or
weak that relationship is.
Methods: Uses statistical measures such as Pearson’s correlation coefficient to analyze data
collected through surveys, observations, or secondary data.
Example: A study examining the correlation between students’ time spent studying and their
exam scores.
Strengths:
Limitations:
Does not provide evidence of causality (correlation does not imply causation).
Relationships between variables may be influenced by third variables.
A diagnostic study design is focused on identifying the causes of a particular problem or phenomenon.
It often involves determining the nature of the problem, the factors contributing to it, and possible
solutions.
Key Characteristics:
Objective: To diagnose the causes and underlying factors of a specific issue or condition.
Methods: May involve interviews, case studies, surveys, or observational techniques to identify
the symptoms, causes, and possible treatments or solutions.
Example: A diagnostic study of poor employee performance in an organization, identifying
factors like low motivation, lack of training, or poor management.
Strengths:
51
Provides insight into the causes of problems, which is valuable for developing interventions.
Helps in problem-solving and decision-making processes.
Limitations:
May be limited in scope and focused on specific cases, making it difficult to generalize findings.
Causal relationships identified might be influenced by external factors not accounted for in the
study.
The quantitative approach to research focuses on the collection and analysis of numerical data to
explain patterns, relationships, or trends. This approach is rooted in the positivist philosophy, which
views reality as objective and measurable.
Key Characteristics:
Objective: To test hypotheses, measure variables, and identify patterns through statistical
analysis.
Methods: Surveys, experiments, observational studies, and secondary data analysis.
Data: Numerical, which is analyzed using statistical tools (e.g., mean, standard deviation,
regression analysis).
Strengths:
Limitations:
1. Surveys:
o Uses structured questionnaires or interviews to collect data from a large group of
respondents.
o Example: A survey of 1,000 people measuring political attitudes and voting behavior.
2. Experiments:
52
o Involves manipulating one or more variables to observe the effect on other variables.
o Example: A lab experiment testing the effect of sleep deprivation on cognitive
performance.
3. Observational Studies:
o Researchers observe subjects without interfering with or manipulating the environment.
o Example: Observing customer behavior in a retail store to understand purchasing
decisions.
4. Secondary Data Analysis:
o Analyzes existing data collected by other researchers or organizations.
o Example: Analyzing government datasets to study trends in unemployment.
Quantitative data analysis involves applying statistical techniques to analyze and interpret numerical
data. Depending on the research question and data collected, different types of analyses can be used:
Key Techniques:
1. Descriptive Statistics:
o Summarizes and describes the basic features of the data, such as mean, median, mode,
and standard deviation.
o Example: Describing the average income of a sample group in a study.
2. Inferential Statistics:
o Used to make inferences or predictions about a population based on sample data.
Common techniques include regression analysis, ANOVA (Analysis of Variance), and t-
tests.
o Example: Using a t-test to determine whether there is a statistically significant
difference in test scores between two groups of students.
3. Correlation and Regression Analysis:
o Correlation measures the strength and direction of a relationship between two
variables.
o Regression goes further by predicting the value of one variable based on another.
o Example: Using linear regression to predict sales based on advertising spending.
The quantitative approach offers several advantages that make it a popular choice for research across
various fields:
53
o Quantitative research can handle large datasets, providing more robust and
generalizable results that are applicable to wider populations.
3. Precision:
o Quantitative methods allow for precise measurements and the ability to test hypotheses
with statistical significance.
4. Comparability:
o Results from quantitative studies can be compared across different groups, regions, or
time periods, facilitating trend analysis and policy-making.
5. Efficiency:
o Well-constructed surveys or experiments can efficiently collect large amounts of data,
which can be processed and analyzed quickly with the right tools.
This comprehensive overview provides insight into various study designs and the strengths and methods
of the quantitative approach
While the quantitative approach has many strengths, it also has certain limitations and disadvantages:
1. Lack of Depth:
o Quantitative research tends to focus on breadth rather than depth. It often overlooks
the complexity of human behavior and experiences, leading to superficial conclusions
about phenomena that require more nuanced understanding.
2. Limited Flexibility:
o Once a quantitative study is designed, it can be difficult to adjust or change variables or
methods mid-study without affecting validity, unlike qualitative research, which can
evolve during the process.
3. Context Ignored:
o Quantitative methods usually strip away contextual factors, focusing solely on
measurable data. This makes it harder to interpret findings in a broader social or cultural
context.
4. Potential for Bias in Data Collection Tools:
o The structure of surveys, questionnaires, or experiments can sometimes lead to biased
responses if the questions are not well-formulated or if certain populations are
underrepresented.
5. Oversimplification of Human Experience:
o Reducing complex human behaviors and emotions into numerical values may fail to
capture the full spectrum of experiences or attitudes, especially in studies related to
social sciences.
6. Data Collection Methods Can Be Restrictive:
o Many quantitative methods rely on surveys or predefined scales, limiting respondents’
ability to provide in-depth answers or explain their choices.
54
7.19 The Mixed Methods Approach
Mixed methods research combines both quantitative and qualitative approaches, providing a more
comprehensive understanding of the research problem. It draws from the strengths of both methods to
address research questions that might be too complex for a single approach.
Characteristics:
Combination of Data: Mixed methods collect and analyze both numerical and non-numerical
data.
Philosophical Foundation: Often based on pragmatism, which focuses on using whatever
methods are necessary to answer the research question.
Example:
A study on employee satisfaction might use surveys (quantitative) to collect data on overall
satisfaction levels and in-depth interviews (qualitative) to explore the reasons behind the
ratings.
The mixed methods approach emerged as researchers recognized the limitations of using purely
quantitative or qualitative methods to address complex research problems. It evolved from the need for
a more flexible, integrative approach that could handle both the generalizability of quantitative data and
the contextual depth of qualitative research.
Development Timeline:
In the 1980s and 1990s, researchers in fields like education, sociology, and healthcare began
integrating both methods to obtain richer insights.
The approach became more formalized with the publication of seminal works that outlined how
to effectively combine qualitative and quantitative research.
1. Integration of Data:
o The core of mixed methods research is the integration of qualitative and quantitative
data, either by merging the data, connecting it, or embedding one type within the other.
2. Sequential or Concurrent Timing:
o Mixed methods can either occur sequentially (one method follows the other) or
concurrently (both methods are conducted at the same time).
55
3. Equal or Dominant Weight:
o Both methods can have equal weight in the research process, or one can be dominant
depending on the research goals. For example, a study might rely primarily on
quantitative data but supplement it with qualitative insights.
4. Purpose:
o Mixed methods are used to triangulate findings, gain deeper insights, and explore
different aspects of a research problem that cannot be adequately addressed by one
method alone.
1. Timing:
o Whether the quantitative and qualitative phases occur sequentially (one after the
other) or concurrently (at the same time).
2. Weight:
o The relative emphasis placed on each method. Is the research primarily quantitative
with a qualitative supplement, or vice versa?
3. Purpose:
o The reason for using mixed methods. For example, researchers might use qualitative
data to explore a phenomenon, then use quantitative data to test findings.
4. Integration:
o How the data is combined. Is one method embedded within the other, or are the
findings from both methods merged to provide a complete picture?
Mixed-method research is highly versatile and can be applied in various fields where complex research
questions require a more comprehensive approach.
Application Fields:
Healthcare: A study might measure patient outcomes quantitatively while using qualitative
interviews to explore patient experiences with treatment.
Education: Teachers' attitudes towards a new teaching method could be quantified through
surveys, while classroom observations and interviews offer in-depth perspectives.
Social Sciences: Researchers could assess the effects of social interventions quantitatively, while
in-depth interviews explore the lived experiences of participants.
56
To triangulate data: Cross-check findings from different sources or methods to ensure
robustness.
To explore and test: Use qualitative methods to explore new phenomena and quantitative
methods to confirm or test hypotheses.
To gain richer insights: Combine the strengths of both approaches to understand the
phenomenon more holistically.
1. Research Problem:
o The nature of the research problem often dictates the approach. If the problem is well-
defined and measurable, a quantitative approach may be preferred. If the problem
involves understanding personal experiences or social dynamics, qualitative methods
may be better suited.
2. Research Questions:
o Quantitative methods are often used for questions that ask “what,” “how much,” or “to
what extent.” Qualitative methods answer questions about “how” or “why” phenomena
occur.
3. Audience:
o The preferences and expectations of the research audience (e.g., journal editors,
funding bodies, stakeholders) may influence the chosen method.
4. Resources:
o The availability of time, funding, and expertise may also influence the decision. For
example, mixed methods research may require more time and resources than a single-
method approach.
Defining the research problem and formulating research questions are critical steps in the research
process. These guide the choice of methodology and influence the type of data collected.
Research Problem:
A well-defined research problem outlines the issue or gap that the research aims to address. It
sets the focus and scope of the study.
Research Questions:
57
Research questions should be clear, focused, and researchable. They determine the type of data
needed, whether the research will be exploratory, descriptive, or explanatory, and whether a
qualitative, quantitative, or mixed-method approach is appropriate.
7.26 Audience
The audience for research includes the individuals or groups who will read, use, or benefit from the
research findings. The audience influences several aspects of the research process:
Types of Audience:
Academic community: Researchers and scholars may expect rigorous, evidence-based findings.
Policy-makers: They may prefer actionable insights derived from mixed-method research that
can inform policy decisions.
Practitioners: Professionals in fields like healthcare, education, or business might prefer
practical recommendations based on real-world data.
Audience preferences can shape the choice of methodology, the presentation of results, and the
overall approach. For instance, if a study is intended for policy-makers, mixed methods might be
used to provide both data-driven evidence and rich qualitative insights.
A researcher’s personal experiences can also influence their choice of research approach. Personal
biases, prior knowledge, and familiarity with certain methods can shape the way a research project is
designed and conducted.
Influence on Research:
A researcher with a background in quantitative analysis may feel more comfortable designing
and conducting studies that rely on statistical techniques.
Alternatively, researchers who have experience with ethnography or interviewing may prefer
qualitative methods that allow for rich, detailed exploration of social phenomena.
Reflexivity in Research:
Researchers should be aware of their personal biases and how these may influence the study.
Reflexivity involves actively reflecting on one’s role in the research process and the potential
impact of personal experiences on data collection and analysis.
58
These sections give an in-depth understanding of the mixed methods approach, the criteria for selecting
research methods, and the roles of the research problem, audience, and personal experiences in
shaping research design.
The Mixed-Methods approach integrates both quantitative and qualitative research methods to gain a
comprehensive understanding of a research problem. This approach is used when neither quantitative
nor qualitative methods alone can fully address the complexity of the research questions.
Key Features:
1. Combines Data Types: Uses numerical data (quantitative) for measuring and testing hypotheses,
while also incorporating non-numerical data (qualitative) to explore deeper meanings and
contexts.
2. Integration of Findings: Both types of data are combined or compared to provide a fuller picture
of the research problem.
3. Sequential or Concurrent: Methods can be implemented one after another (sequentially) or
simultaneously (concurrently), depending on the research design.
4. Flexibility: Allows researchers to explore, describe, and test research questions in a flexible and
holistic manner.
Example:
A study on employee satisfaction might use surveys (quantitative) to measure satisfaction levels
and interviews (qualitative) to explore why employees feel satisfied or dissatisfied.
Comprehensive Insight: Captures both the measurable aspects of a phenomenon and the
deeper meanings behind it.
Triangulation: Helps validate results by cross-verifying data from both quantitative and
qualitative sources.
Enhanced Contextual Understanding: Quantitative data provides generalizable results, while
qualitative data gives insight into individual experiences.
When selecting a research approach, several factors should be considered to ensure that the
methodology aligns with the research goals, context, and resources available.
Quantitative approach: Best suited for well-defined problems where relationships between
variables can be measured (e.g., testing hypotheses, determining trends).
59
Qualitative approach: Useful for exploratory research, where the goal is to understand
experiences, perceptions, or complex social processes.
Mixed Methods approach: Selected when the problem requires both measurable data and in-
depth exploration of context and meaning.
2. Research Questions:
3. Audience:
The expectations of the target audience (e.g., scholars, policymakers, practitioners) influence
the method:
o Academics may expect rigorous, data-driven studies (quantitative).
o Policy-makers or practitioners may prefer research that includes both evidence and rich
context (mixed methods).
4. Resources:
Consider the time, expertise, and budget available. Quantitative methods often require
statistical tools and large sample sizes, while qualitative methods might require more time for
interviews and analysis. Mixed Methods research can demand more resources since it involves
both.
In summary, the Mixed-Methods approach offers a versatile way to address complex research
questions by integrating the strengths of both qualitative and quantitative methods. The norm for
selecting a research approach is guided by the nature of the research problem, the questions posed, the
audience's needs, the resources available, and the researcher's own experience.
UNIT 8
8.1 Sampling
60
Sampling is the process of selecting a subset of individuals, events, or elements from a larger population
to participate in a study. Researchers use samples to make inferences about the entire population
without studying every individual.
Size of a Sample
Prior to choosing how enormous a Sample should be, you need to characterize your
examination Population (who you are incorporating and barring in your investigation). The
subject of how enormous a Sample should be is a troublesome one. Test size can be dictated
by different imperatives (subsidizing accessible, the time limitations and so forth) Sample
size relies upon
• The kind of information examination to be performed
• The ideal accuracy of the assessments one wishes to accomplish
• The sort and number of correlations that will be made
61
Purpose of Sampling
The primary purpose of sampling is to allow researchers to make inferences about a larger population
by studying a smaller, manageable group of individuals or elements. Sampling is essential because, in
many cases, studying the entire population is impractical due to limitations of time, cost, and
accessibility.
1. Generalization:
o A well-chosen sample allows researchers to generalize findings to the entire population.
2. Efficiency:
o Sampling is much more cost-effective and time-efficient than studying an entire
population.
3. Practicality:
o It is often impossible to collect data from every individual in a large population,
especially in studies involving human behavior, opinions, or preferences.
4. Focus:
o Sampling enables researchers to concentrate on a subset of the population that is most
relevant or accessible, making it easier to conduct detailed investigations.
Example:
In a political poll, researchers might survey 1,000 people to predict the voting behavior of millions in an
election.
Sampling Error
Sampling error refers to the difference between the results obtained from the sample and the actual
parameters of the population. It arises because the sample is not a perfect representation of the
population, even when selected randomly. The smaller the sampling error, the closer the sample results
are to the true population values.
1. Sample Size:
o Smaller samples tend to have larger sampling errors because they are less likely to
represent the population accurately.
2. Random Variation:
o Even in a random sample, chance may cause the sample to differ from the population,
especially if the population is highly diverse.
3. Sampling Method:
62
o The method of selecting a sample (e.g., random, stratified) can influence the likelihood
of sampling error.
Increase the sample size: A larger sample size typically reduces sampling error.
Use appropriate sampling techniques: Proper methods like stratified sampling help ensure that
different population segments are adequately represented.
Sampling Bias
Sampling bias occurs when the sample selected is not representative of the population, leading to
inaccurate or misleading conclusions. This bias results from flaws in the sampling process and can
seriously compromise the validity of the research.
1. Non-Random Selection:
o If certain groups within the population are systematically excluded or over-represented,
the sample will be biased (e.g., convenience sampling where only easily accessible
participants are selected).
2. Undercoverage:
o When some segments of the population are not adequately represented in the sample,
the results may not reflect the population accurately.
3. Self-Selection Bias:
o Occurs when individuals decide for themselves whether to participate in the study,
potentially leading to an unrepresentative sample (e.g., voluntary surveys).
4. Response Bias:
o Bias can also occur if participants provide inaccurate or dishonest responses, or if
certain groups are less likely to respond at all.
Use Random Sampling: Ensure that every individual in the population has an equal chance of
being selected.
Stratify the Sample: Divide the population into subgroups (strata) and select samples from each
stratum to ensure proportional representation.
Importance of Sampling:
63
Manageable data: Sampling allows researchers to work with a smaller, more manageable
amount of data.
Example:
If a company wants to understand employee satisfaction, they might survey a sample of 200 employees
from a workforce of 1,000 rather than surveying every employee.
Population: The complete set of individuals, items, or events of interest for a particular study. It
can be large (e.g., all students in a country) or small (e.g., all employees in a company).
Sample: A subset of the population selected for the study. The goal is for the sample to
represent the population as accurately as possible.
A good sample should be representative and reflect the characteristics of the population. The key
characteristics of a good sample include:
1. Representativeness:
o The sample should accurately represent the population’s diversity in terms of important
variables (e.g., age, gender, socioeconomic status).
2. Randomness:
o A good sample is selected randomly to avoid bias. Every member of the population
should have an equal chance of being included.
3. Adequate Size:
o The sample size must be large enough to allow for accurate inferences about the
population. Small samples can lead to unreliable results.
4. Lack of Bias:
o A sample should be free from bias that could distort the findings (e.g., selecting only
certain groups that favor one outcome).
64
8.4 Size of a Sample
The size of a sample is critical to ensuring that the results of the study can be generalized to the
population. Several factors influence the required sample size:
1. Population Size:
o The larger the population, the larger the sample needs to be to accurately reflect it.
However, in very large populations, the sample size plateaus after a certain point.
2. Margin of Error:
o A smaller margin of error requires a larger sample size. The margin of error indicates
how close the sample’s findings are to the true population value.
3. Confidence Level:
o A higher confidence level (e.g., 95% or 99%) requires a larger sample size. The
confidence level tells us how certain we can be that the sample findings are
representative of the population.
4. Variability:
o If the population is highly diverse, a larger sample size is needed to capture that
variability.
Example:
In a population of 1,000 people, if we want to achieve a 95% confidence level with a 5% margin
of error, a sample size of around 278 people might be required. However, the size would differ
based on the variability within the population.
There are two main categories of sampling: probability sampling and non-probability sampling. These
categories encompass various types of sampling methods.
1. Probability Sampling:
In probability sampling, each member of the population has a known, non-zero chance of being
selected. This is often considered the more rigorous method because it aims to produce representative
samples.
Simple Random Sampling: Each member of the population has an equal chance of being
selected.
Systematic Sampling: Every nth member of the population is selected after arranging the
population in some order.
Stratified Sampling: The population is divided into subgroups (strata), and random samples are
drawn from each stratum. This ensures representation across key subgroups.
65
Cluster Sampling: The population is divided into clusters (usually based on geography), and
entire clusters are randomly selected for the study.
2. Non-Probability Sampling:
In non-probability sampling, not every member of the population has a known chance of being included,
which may introduce bias but is often used in exploratory research or when probability sampling is
impractical.
These sections cover the essentials of sampling, including the functions, characteristics of a good
sample, sample size considerations, and various types of sampling methods. Each of these elements
plays a crucial role in ensuring the validity and reliability of research results
UNIT NO 9
Research strategies are overarching plans that guide researchers in the systematic investigation of
phenomena. They dictate how data will be collected, analyzed, and interpreted, and can vary
significantly based on the research question and objectives. Common research strategies include:
1. Case Studies: In-depth exploration of a single unit (e.g., individual, group, organization) to
understand complex issues in real-life contexts.
2. Experimental Research: Involves manipulating variables to determine cause-and-effect
relationships. Typically conducted in controlled environments.
3. Ethnography: A qualitative approach focused on understanding the cultural practices and beliefs
of a specific group through immersion in their environment.
4. Phenomenology: Explores and describes lived experiences from the perspective of participants,
aiming to understand the essence of those experiences.
5. Grounded Theory: A systematic methodology that aims to generate or discover theory through
the collection and analysis of data.
66
1. Research Questions:
o Clearly defined questions guide the selection of a strategy. For example, exploratory
questions may favor qualitative strategies like case studies or ethnography, while causal
questions may lean towards experimental research.
2. Nature of the Study:
o Determine whether the study is exploratory, descriptive, or explanatory. Exploratory
studies often utilize qualitative methods, while explanatory studies may require
quantitative approaches.
3. Context and Environment:
o The setting and context of the research can influence strategy choice. Ethnographic
studies are suitable for understanding social contexts, while experimental strategies are
better for controlled settings.
4. Available Resources:
o Consider time, budget, and access to participants. Some strategies may require more
extensive resources than others.
5. Personal Expertise:
o The researcher’s familiarity and comfort with specific methodologies can impact the
effectiveness of the chosen strategy.
Case studies provide an in-depth understanding of a particular case within its real-life context. They can
be used in various disciplines and often involve multiple sources of data.
Characteristics:
1. Defining the Case: Clearly specify what is being studied (individual, group, event).
2. Data Collection: Use multiple sources such as interviews, observations, documents, and surveys.
3. Data Analysis: Analyze data using thematic analysis or other qualitative techniques to identify
patterns and insights.
4. Reporting Findings: Present a comprehensive narrative that conveys insights and conclusions
derived from the case.
67
9.5 Experimental Research Strategy
Experimental research involves manipulating one or more independent variables to observe the effect
on a dependent variable, establishing cause-and-effect relationships.
Key Features:
1. Control: Researchers can control variables, allowing for precise measurement of effects.
2. Causality: Helps establish clear cause-and-effect relationships.
3. Replication: Experimental designs can be replicated by other researchers, enhancing reliability.
Ethnography is a qualitative research strategy focused on exploring the cultural practices and behaviors
of a specific group through direct observation and participation.
Characteristics:
1. In-Depth Understanding: Provides rich, detailed insights into participants’ experiences and
cultural contexts.
2. Flexibility: The researcher can adapt to new findings and directions during the study.
3. Contextual Insights: Captures the complexity of social interactions and cultural practices.
68
3. Generalizability: Findings from one group may not be applicable to other contexts.
Phenomenology focuses on understanding the essence of lived experiences from the perspectives of
individuals.
Characteristics:
Grounded theory aims to generate a theory grounded in data systematically collected and analyzed. It is
particularly useful for exploring areas where existing theories are lacking.
Methodology:
Summary
The choice of research strategy is fundamental to the design and execution of a study. Each strategy has
its own strengths and weaknesses, making it important to align the strategy with research questions,
objectives, and the context of the study. If you need more information on any specific strategy or
further elaboration on methodologies,
69
Grounded Theory is conducted to develop a theory that is grounded in the data collected from
participants rather than testing existing theories. It is particularly useful in areas where little prior
research exists, allowing researchers to explore and understand complex social processes.
1. Theory Development: To create a new theory based on real-world data, providing insights into
specific phenomena.
2. Understanding Processes: To explore how people make sense of their experiences and the
meanings they attribute to them.
3. Flexibility: To adapt and refine theories based on ongoing data collection and analysis, making it
suitable for dynamic and evolving contexts.
1. Data-Driven: Theories developed are directly based on empirical data, enhancing their
relevance and applicability.
2. Flexibility: Researchers can modify their approach as new data emerges, allowing for an
adaptive research process.
3. Rich Insights: Provides deep insights into participants' perspectives, helping to uncover
underlying social processes and relationships.
4. Iterative Process: Involves constant comparison and analysis, which enhances the depth and
rigor of the research.
1. Complexity: The process can be intricate and time-consuming, requiring careful attention to
detail in coding and analysis.
2. Subjectivity: The researcher’s interpretations can introduce bias, which may affect the findings
and the theory developed.
3. Resource Intensive: Requires substantial time and effort in data collection, analysis, and theory
formulation.
4. Limited Generalizability: Findings may not be easily generalizable to other contexts, especially if
based on a small sample size.
The process of conducting research using Grounded Theory typically involves several key steps:
1. Data Collection:
o Gather qualitative data through interviews, observations, or focus groups.
70
2. Initial Coding:
o Analyze the data through open coding to identify initial concepts and categories.
3. Axial Coding:
o Reorganize the data by linking categories and subcategories, focusing on their
relationships and contexts.
4. Selective Coding:
o Integrate and refine categories to develop a core category that represents the main
theme of the research.
5. Theory Development:
o Construct a grounded theory that explains the patterns observed in the data,
incorporating the relationships between categories.
6. Validation:
o Compare findings with existing literature and gather feedback from participants to
validate the developed theory.
The analysis of research strategies involves evaluating their effectiveness in addressing research
questions. This includes:
Action Research is a participatory research strategy aimed at solving a specific problem while
simultaneously generating knowledge. It involves collaboration between researchers and participants to
effect change and improve practices.
Characteristics:
71
9.19 Major Theoretical Approaches
In research, various theoretical approaches guide the design and analysis, including:
Mixed Research Strategy combines both quantitative and qualitative research methods to provide a
more comprehensive understanding of research questions. This approach is beneficial when:
Key Considerations:
Longitudinal Research involves repeated observations of the same variables over a period of time. It is
particularly useful for studying changes and developments in a population or phenomenon.
Characteristics:
Advantages:
1. Change Over Time: Allows researchers to observe how variables change and evolve over time.
2. Causality: Helps establish causal relationships by examining the temporal order of events.
3. Rich Data: Provides comprehensive data that captures the dynamics of subjects over time.
72
Challenges:
Resource Intensive: Requires significant time and commitment from both researchers and
participants.
Attrition: Participants may drop out of the study over time, which can affect the validity of
findings.
Summary
4o mini
73