RESEARCH METHODS IN PSYCHOLOGY

Teacher – Prof. Anand Gore

UNIT 1 OVERVIEW OF RESEARCH PROCESS AND SURVEY RESEARCH

1.1 Meaning and Types of research, Overview of basic research concepts; Ethical issues
in research

meaning and types of research

Research is a systematic process of investigating and exploring ideas, phenomena, or

issues to gain new knowledge, validate existing knowledge, or solve specific problems. It
involves the collection, analysis, and interpretation of data to draw conclusions and make
informed decisions. Research can be broadly classified into several types based on
different criteria, such as the purpose, methods, and nature of the investigation. Here are
the main types:
1. Based on Purpose
Basic (Pure) Research
Basic research, also known as fundamental or pure research, is conducted to increase
knowledge and understanding of fundamental principles. It is not aimed at solving
practical problems but rather at expanding scientific understanding.
Studying the structure of atoms, exploring the fundamental laws of physics, or
understanding the cognitive processes involved in memory.
Applied Research
Applied research is designed to solve specific, practical problems. It uses the findings
from basic research to address real-world issues and improve human conditions.
Developing new treatments for diseases, improving educational methods, or
enhancing workplace productivity.

2. Based on Methods
Quantitative Research
Quantitative research involves collecting and analyzing numerical data to quantify
variables and identify patterns, relationships, or trends. It often uses statistical
techniques to test hypotheses.

1
 Methods: Surveys, experiments, structured observations, and secondary data analysis.
Measuring the effect of a new drug on blood pressure, assessing customer satisfaction
through a survey, or analyzing crime rates in a city.

Qualitative Research
and perspectives of participants. It involves collecting non-numerical data and often
explores complex phenomena in-depth.
Methods: Interviews, focus groups, ethnography, case studies, and content analysis.
Exploring the lived experiences of cancer survivors, understanding cultural practices
through ethnographic studies, or analyzing the themes in political speeches.

Mixed-Methods Research
Mixed-methods research combines quantitative and qualitative approaches to provide
a more comprehensive understanding of a research problem.
Examples: A study on education outcomes that uses standardized test scores
(quantitative) and interviews with students and teachers (qualitative) to explore
underlying factors.

3. Based on Nature

Descriptive Research
Descriptive research aims to describe characteristics, behaviors, or phenomena as they
exist. It does not involve manipulating variables but rather observes and records
information.
Methods: Surveys, observational studies, case reports, and archival research.
Examples: A census that describes demographic characteristics, a study describing
consumer preferences, or an observation of animal behavior in a natural habitat.

Exploratory Research
Exploratory research is conducted to explore a problem or phenomenon that is not
well understood. It aims to gather preliminary information that will help define the
problem and suggest hypotheses.
Methods: Literature reviews, expert interviews, focus groups, and pilot studies.

2
 Examples: Investigating emerging trends in technology, exploring new markets for a
product, or understanding the initial impact of a new policy.
Explanatory (Causal) Research
Explanatory research seeks to explain the cause-and-effect relationships between
variables. It aims to determine why things happen and predict future occurrences.
Methods: Experiments, longitudinal studies, and regression analysis.
Studying the effects of a new teaching method on student performance, examining the
impact of advertising on consumer behavior, or exploring the causes of a public health
crisis.

4. Based on Time Frame

Cross-Sectional Research
Cross-sectional research involves observing or collecting data from a population or a
representative subset at one specific point in time.
Examples: A survey measuring public opinion on a current event, a study assessing
the prevalence of a disease at a particular time, or an analysis of market conditions in
a specific quarter.

Longitudinal Research
Longitudinal research involves studying the same subjects over an extended period to
observe changes and developments.
Examples: A long-term study on the development of children, tracking the career
progression of graduates, or following the health outcomes of a cohort of patients over
several years.

5. Based on Data Sources

Primary Research
Primary research involves collecting original data directly from sources such as
experiments, surveys, or observations.
Examples: Conducting an experiment to test a new drug, running a survey to gather
customer feedback, or observing social interactions in a specific setting.

3
 Secondary Research
Secondary research involves analyzing existing data collected by others, such as data
from books, articles, reports, or databases.

Examples: Reviewing published studies on climate change, analyzing census data, or

conducting a meta-analysis of research findings in a specific field.

Each type of research has its unique strengths and limitations, and the choice of which
type to use depends on the research question, objectives, and available resources.

Ethical issues in research

Ethical issues in research are crucial to ensuring that studies are conducted responsibly
and with respect for participants.

1. Informed Consent
Participants must be fully informed about the nature, purpose, risks, and benefits of the
research before agreeing to participate. In a study investigating the effects of a new
treatment, participants should be informed about potential side effects, the experimental
nature of the treatment, and their right to withdraw at any time without penalty.
Researchers provide a detailed consent form and ensure participants understand
the information.

2. Confidentiality
Participants’ personal information and data must be kept confidential and protected from
unauthorized access. In a survey about sensitive topics like mental health, researchers
must ensure that responses are anonymized and stored securely to prevent breaches of
privacy.
Researchers use de-identification methods and secure data storage systems. They also
clearly communicate how data will be used and protected.

3. Deception

4
Deception involves misleading participants about the true nature of the study. While
sometimes necessary, it must be used cautiously. In a study on social behavior,
participants might be told they are interacting with another participant when they are
actually interacting with a researcher. Deception should be justified, and participants must
be debriefed afterward. The deception should not cause harm or distress, and the benefits
of the research should outweigh the use of deception.

4. Right to Withdraw
Participants have the right to withdraw from the study at any time without penalty or loss
of benefits.
If a participant feels uncomfortable during a study, they should be able to leave without
facing any negative consequences. Researchers ensure participants are aware of their right
to withdraw and facilitate an easy exit process if needed.

5. Risk of Harm
Researchers must minimize any potential physical or psychological harm to participants.
In a study involving exposure to distressing content, researchers should assess and
minimize potential emotional impact and provide support resources.
Conduct risk assessments, implement safety measures, and offer counseling or support if
necessary. The benefits of the research should justify any potential risks.

6. Vulnerable Populations
Special considerations are needed when working with populations who may have
diminished capacity to provide informed consent, such as children, individuals with
cognitive impairments.
When conducting research with children, researchers must obtain consent from parents or
guardians and assent from the children themselves.
Implement additional safeguards to ensure that vulnerable participants are treated with
respect and their rights are protected.

7. Integrity and Honesty

Researchers must conduct their work with integrity, avoiding fabrication, falsification,
and plagiarism.

5
 Researchers should report all results honestly, even if the data does not support their
hypotheses, and properly cite sources and contributions. Follow established guidelines for
research conduct, maintain transparency, and uphold high standards of academic integrity.

1.2 Sampling Technique

Probability Sampling: Allows for statistical inference and generalization to the

population, reducing sampling bias and providing more accurate and reliable
results. It requires a complete sampling frame and can be more time-consuming
and costly.

Non-Probability Sampling: Easier and quicker to implement, useful for

exploratory research or when a sampling frame is not available. However, it is
more prone to sampling bias and limits the ability to generalize findings to the
larger population.

6
Random Sampling: This technique ensures that each member of the population has an

equal chance of being selected. For example, if a psychologist wants to study the stress

levels of college students, they could use a computer program to randomly select 100

students from the university’s student registry. This method minimizes bias and helps

ensure that the sample represents the larger student population.

It Emphasized for its ability to eliminate selection bias. For instance, to study job

satisfaction among factory workers, a random sample of workers from different shifts and

departments could be selected. This ensures that the sample represents the entire

workforce.

Simple Random Sampling: Detailed discussion on implementation and importance. For

example, to study the prevalence of anxiety among college students, researchers could

randomly select a sample from the student enrollment list, ensuring each student has an

equal chance of being chosen.

Stratified Sampling: In this method, the population is divided into subgroups (strata)

based on specific characteristics (e.g., gender, age). For instance, to study the impact of a

new teaching method, researchers might divide students into strata based on their grade

levels and then randomly select an equal number of students from each grade. This

ensures that all grade levels are adequately represented.

Useful for ensuring diverse representation. For instance, if researching the impact of

social media use across different age groups, the population could be divided into age

strata (e.g., 18-25, 26-35) and random samples taken from each stratum. This ensures that

all age groups are adequately represented in the study.

Cluster Sampling: This technique involves dividing the population into clusters, often

based on geography, and then randomly selecting entire clusters. For example, a

7
researcher studying teaching methods might select a few schools randomly from a district

and then study all teachers within those schools. This method is practical for large

populations spread over wide areas.

Systematic Sampling: Every nth member of the population is selected after a random

start. For instance, if a researcher wants to survey every 10th student entering the library,

they would start at a random point and then select every 10th student thereafter. This

method is easier to implement than simple random sampling and still maintains

randomness.

Purposive Sampling: Participants are selected based on specific characteristics or

qualities. For example, if researching coping mechanisms among individuals with chronic

illness, the researcher might specifically choose participants who have been living with

the illness for over five years. This ensures that the data collected is rich and relevant to

the research question.

Snowball Sampling: Current participants recruit future participants from among their

acquaintances. For example, in studying a rare psychological condition, the researcher

might start with a few known cases and ask these participants to refer others who also

have the condition. This method helps reach populations that are hard to access.

Convenience Sampling: Participants are chosen based on their availability and

willingness to participate. For instance, a psychologist conducting a study on sleep

patterns might survey students in a particular class because they are readily accessible.

8
Although easy to implement, this method can introduce significant bias and limit the

generalizability of the findings.

Quota Sampling: Researchers fill quotas for different subgroups to ensure

representation. For example, in a study on attitudes towards mental health services, the

researcher might set quotas to include 50 men and 50 women. Although the selection

within each subgroup is non-random, this method ensures diversity.

Judgmental Sampling: Participants are selected based on the researcher's judgment and

knowledge. For example, a researcher studying leadership styles might select managers

known for their distinct leadership approaches. This method relies on the researcher's

expertise to choose the most informative participants.

Sequential Sampling: This method continues sampling until a specific criterion is met,

such as data saturation. For example, in a qualitative study on therapy outcomes, the

researcher might interview participants until no new themes emerge from the data. This

ensures comprehensive coverage of the research topic.

Proportional Sampling: Ensures that subgroups within the population are represented

proportionally. For example, if a population has 30% females and 70% males, the sample

should reflect this ratio. This technique is crucial in behavioral sciences to accurately

reflect the diversity of the population.

9
10
1.3. Methods of data collection: Primary data and secondary data; selection

of appropriate method for data collection.

Methods of Data Collection: Primary and Secondary Data

Understanding the different methods of data collection is fundamental in research, as

it influences the quality, reliability, and validity of the findings.

Primary Data Collection -

Primary data is original data collected directly by the researcher for the specific purpose

of addressing a particular research problem or question. This data is considered more

authentic because it is collected firsthand, and the researcher has control over the methods

used. There are several methods of primary data collection:

Surveys and Questionnaires

Surveys and questionnaires are tools for collecting data from a large group of

people in a standardized manner. Surveys can be administered through various means,

such as online forms, paper questionnaires, or face-to-face interviews.

They allow researchers to collect data from a large sample quickly and efficiently,

making it possible to generalize findings to a broader population. The design of

questions is crucial, as poorly worded or biased questions can lead to inaccurate data.

Response rates can also vary depending on the mode of survey administration.

Morgan, and Leech (2017) emphasize the importance of carefully designing surveys

to minimize bias and ensure that the data collected accurately reflects the population

being studied. They also discuss the use of various sampling techniques to enhance

the representativeness of the data.

11
Interviews

Interviews involve direct, face-to-face or virtual interaction between the

researcher and the participant. They can be structured (with predetermined questions),

semi-structured (with a flexible guide), or unstructured (more conversational).

Interviews provide depth and detail, allowing researchers to explore complex

behaviors, motivations, and attitudes. They are particularly useful in qualitative

research where understanding the meaning behind behaviors is crucial.

Interviews can be time-consuming and resource-intensive. There is also a risk of

interviewer bias, where the interviewer’s behavior influences the responses of the

participant. Howitt and Cramer (2020) highlight the flexibility of interviews,

especially in psychological research, where understanding subjective experiences is

essential. They also discuss techniques to reduce bias, such as training interviewers

and using neutral language.

Observations

Observation involves systematically watching and recording behaviors or

events as they naturally occur. Researchers can be participants in the setting they are

studying or non-participant observers. This method provides direct evidence of

behaviors, reducing the likelihood of self-report biases that can occur in surveys or

interviews. It is particularly valuable in studies where behaviors cannot be easily

verbalized.

Observations can be intrusive, and the presence of the researcher may alter the

behavior being studied (known as the Hawthorne effect). Recording and interpreting

observational data can also be subjective. Kerlinger (1994) discusses the importance

12
 of observational methods in behavioral research, particularly in settings where

experimental manipulation is not possible. He stresses the need for objective

recording and analysis of observations to minimize bias.

Experiments

Experiments involve manipulating one or more independent variables to

observe the effect on a dependent variable. This method is particularly powerful for

establishing cause-and-effect relationships. Experiments provide high levels of

control over variables, allowing researchers to isolate the effects of specific factors.

This makes it easier to draw conclusions about causality. The artificial nature of

experimental settings can sometimes limit the generalizability of findings to real-

world situations. Ethical considerations also arise when manipulating variables that

could impact participants' well-being. Zechmeister, & Shaughnessy (2001) describe

experiments as a foundational method in psychological research. They outline the

importance of random assignment and control groups in ensuring the validity of

experimental results.

Secondary Data Collection

Secondary data refers to data that has already been collected by others and is available

for use by researchers. This data can be found in various sources, such as books, journal

articles, government reports, and online databases.

Literature Review

A literature review involves systematically searching, reviewing, and synthesizing

existing research on a particular topic. It helps researchers identify gaps in the literature,

13
refine their research questions, and frame their study within the context of existing

knowledge. It provides a comprehensive overview of the current state of knowledge on a

topic, saving time and resources that would be spent on primary data collection.

The quality of a literature review depends on the thoroughness of the search process

and the researcher’s ability to critically evaluate and synthesize diverse sources. Kothari

(1985) emphasizes the importance of a thorough literature review in grounding research

within the existing body of knowledge. He discusses techniques for efficiently searching for

and reviewing relevant literature.

Archival Research

Archival research involves analyzing existing records or documents to gather data.

This can include historical records, official documents, personal diaries, newspapers, or

digital records. It allows researchers to study trends over time and to access data that would

be difficult or impossible to collect otherwise. Archival data can provide a rich source of

information, particularly for longitudinal studies.

The data may not perfectly align with the researcher’s needs, and there can be issues

with the accuracy, completeness, or bias of the original records. Singh (2006) discusses

archival research as a valuable method when primary data collection is not feasible. He

highlights the importance of verifying the reliability of archival sources and the need for

careful interpretation of historical data.

Meta-analysis

14
 Meta-analysis is a statistical technique that combines the results of multiple studies on

a particular topic to arrive at a general conclusion. It involves systematically reviewing the

literature, selecting studies that meet specific criteria, and synthesizing their findings. It

provides a comprehensive overview of research on a topic and increases the statistical power

by combining data from multiple studies. Meta-analysis can also help identify patterns and

trends that individual studies might miss.

The quality of a meta-analysis depends on the quality of the studies included. There is

also a risk of publication bias, where studies with positive findings are more likely to be

published and included in the analysis. Morgan, and Leech (2017) discuss meta-analysis as a

valuable tool for synthesizing research findings. They emphasize the importance of clear

inclusion criteria and rigorous statistical methods to ensure the validity of the results.

Selection of Appropriate Method

Choosing between primary and secondary data collection depends on several factors,

including the research question, available resources, time constraints, and ethical

considerations.

Nature of the Research Question

If the research question requires specific, up-to-date information that is not available

in existing sources, primary data collection is necessary. For example, studying current

consumer preferences or psychological states requires direct engagement with participants.

If the research question can be addressed using existing data, secondary data may be

sufficient. For instance, historical analyses or trend studies can often rely on archival data.

The importance of aligning the data collection method with the research question. For

15
example, qualitative research often requires primary data collection to capture the depth and

complexity of psychological experiences.

Resources and Time Constraints

Collecting primary data can be time-consuming and resource-intensive, requiring

careful planning, recruiting participants, and ensuring ethical compliance. It may not be

feasible in all situations, particularly when resources are limited. Secondary data is often

more cost-effective and quicker to obtain, as the data has already been collected. However, it

may not be as tailored to the specific research question as primary data.

Validity and Reliability

Primary data is generally more valid and reliable because it is collected specifically

for the research purpose. The researcher has control over the data collection process, which

can enhance the accuracy and relevance of the data. Secondary data may have limitations in

validity and reliability, as it was collected for different purposes. Researchers must critically

evaluate the quality and relevance of the data before using it in their studies.

According to Kerlinger (1994) highlights the importance of validity and reliability in

research, noting that while primary data offers higher validity, secondary data can be useful

when carefully evaluated and appropriately applied.

Ethical Considerations

16
 When collecting primary data, ethical considerations are paramount. Researchers

must obtain informed consent from participants, ensure confidentiality, and avoid causing

harm. These ethical responsibilities can add complexity to the data collection process.

Secondary data collection generally involves fewer ethical concerns, as the data has already

been collected and anonymized. However, researchers must still ensure that they use the data

responsibly and acknowledge the original sources. Zechmeister discuss the ethical

implications of different data collection methods, particularly in psychological research,

where the well-being of participants is a central concern.

17
1.4. Survey research designs- Cross-sectional, successive independent

samples, longitudinal

1. Cross-Sectional Design

A cross-sectional design involves collecting data from a population or a representative subset

at a single point in time. It provides a "snapshot" of the population, allowing researchers to

analyze and compare different groups within the population simultaneously.

Key Characteristics:

Single Time Point: Data is collected only once, meaning all participants provide their

responses during the same time frame.

Comparative Nature: Researchers often compare different groups (e.g., age, gender,

socioeconomic status) within the population at that single point in time.

Descriptive and Correlational: This design is primarily used to describe

characteristics of a population and examine relationships between variables. However,

it cannot establish causality.

2. Successive Independent Samples Design

In this design, researchers conduct a series of cross-sectional studies at different time points

using different samples from the same population. Each sample is independent, meaning that

the individuals participating in each survey are not the same.

Key Characteristics:

Multiple Cross-Sections: Data is collected at various time points, but each time, a

new sample is drawn from the population.

18
 Trend Analysis: This design is ideal for observing trends over time by comparing

results from different surveys conducted at different times.

Population-Level Insights: It provides insights into how a population's

characteristics or behaviors change over time.

3. Longitudinal Design

A longitudinal survey design involves collecting data from the same group of individuals (the

same sample) at multiple time points. This design allows researchers to track changes over

time, providing insights into developmental trends, causal relationships, and the stability of

certain characteristics or behaviors.

Key Characteristics:

Repeated Measures: The same participants are surveyed repeatedly over time,

allowing researchers to observe how individuals change or remain stable.

Time-Span: Longitudinal studies can span from a few months to several decades,

depending on the research objectives.

Causal Relationships: Because it tracks changes over time, this design is well-suited

for establishing causal relationships between variables.

Choosing the Appropriate Design

Selection Criteria:

Research Objectives: If the goal is to understand the prevalence or distribution of a

phenomenon at a specific time, a cross-sectional design may be best. For tracking

19
trends over time without individual-level focus, a successive independent samples

design is appropriate. If the research requires understanding changes over time at the

individual level, a longitudinal design is necessary.

Resources: Longitudinal studies require more resources and time, so researchers must

consider whether they have the means to conduct such a study.

Data Needs: Consider whether the research question requires data on trends, causal

relationships, or simple associations. This will guide the choice of design.

20
1.5. APA style of preparing research proposal & writing research report

I. APA Style Research Proposal

A research proposal is a document that outlines your planned research. It serves to present

the research problem, the significance of the study, and the proposed methodology to be

used in conducting the research. The proposal should convince readers of the importance

and feasibility of the research.

1. Title Page

Title: The title should be concise yet descriptive, reflecting the key focus of the

research. It should not exceed 12 words.

Author’s Name: Your full name should be centered on the page, just below the title.

Institutional Affiliation: The name of your academic institution or organization

should be cantered below your name.

Running Head: A shortened version of your title (no more than 50 characters,

including spaces), placed in the header on the left margin of every page, including the

title page.

Page Number: Start with page number 1 on the title page, placed in the header on the

right margin.

2. Abstract

Length: The abstract should be a single paragraph, typically between 150-250 words.

Content: Summarize the key elements of the research proposal, including the

research question, hypothesis (if applicable), methods, and expected outcomes. The

abstract should be clear, concise, and self-contained.

Keywords: After the abstract, list 3-5 keywords that encapsulate the main topics of

the research. These help with indexing and searching.

21
3. Introduction

The introduction section provides the foundation for your research by outlining the

background, significance, and objectives of your study.

Background: Begin with an overview of the research topic, including relevant

theories, concepts, and previous research. Provide sufficient context to explain why

the research is necessary.

Research Problem: Clearly state the specific problem or question your research will

address. Explain the gap in knowledge or the specific issue that your research aims to

fill or solve.

Purpose of the Study: Describe the main objectives of your research. What do you

hope to achieve or discover through this study?

Significance: Explain the importance of your research. How will it contribute to the

field? What are the potential theoretical, practical, or societal implications?

Hypotheses or Research Questions: If applicable, state the hypotheses that your

study will test or the specific research questions that will guide your inquiry.

Literature Review: Conduct a brief review of the existing literature on your topic.

Summarize key studies, highlight relevant findings, and identify gaps that your

research will address. This section sets the stage for your study by demonstrating

familiarity with the field and establishing a framework for your research.

4. Method

The method section outlines the research design, participants, instruments, and

procedures you will use to conduct your study. This section should be detailed enough

that another researcher could replicate your study.

22
 Participants: Describe the participants in your study, including the number of

participants, demographic characteristics (e.g., age, gender, ethnicity), and how they

will be selected (e.g., random sampling, convenience sampling). Also, mention any

inclusion or exclusion criteria.

Materials/Instruments: List and describe any materials or instruments you will use

to collect data, such as surveys, questionnaires, tests, or software. Include information

on the reliability and validity of these instruments if available.

Procedure: Provide a step-by-step account of how the research will be conducted.

Include details on how participants will be recruited, what they will be asked to do,

the timeline of the study, and how data will be collected. If your study involves an

experimental design, explain how participants will be assigned to conditions.

Design: Specify the overall research design (e.g., experimental, correlational,

observational) and identify the variables of interest. If you are using an experimental

design, define the independent and dependent variables, as well as any control or

extraneous variables.

5. Expected Results

In this section, describe the potential outcomes of your research. What do you expect to

find?

Predictions: Based on your research hypotheses or questions, predict the outcomes

you expect from your study. For example, if you are testing a hypothesis, state

whether you expect it to be supported or not.

Implications: Discuss the possible implications of your expected results. How will

these results contribute to the existing knowledge in the field? What practical

applications might they have? Consider both theoretical and practical implications.

23
6. References

Formatting: List all the references cited in your proposal in APA style. Start the

reference list on a new page, with the title "References" centered at the top.

Order: Arrange references alphabetically by the last name of the first author.

Hanging Indent: Use a hanging indent for each reference entry, where the first line of

each entry is flush left, and subsequent lines are indented.

7. Appendices (if needed)

 Additional Material: Include any additional materials that support your proposal,

such as questionnaires, consent forms, or detailed descriptions of instruments. Label

each appendix (e.g., Appendix A, Appendix B) and refer to them in the text where

appropriate.

II. APA Style Research Report

A research report details the process, results, and conclusions of a completed study. It

includes sections that describe the research methodology, present the findings, and

discuss the implications.

1. Title Page

Similar to the research proposal, the title page should include the title, author’s name,

institutional affiliation, running head, and page number.

2. Abstract

Length: The abstract should be a single paragraph, typically 150-250 words.

24
 Content: Summarize the entire research report, including the research problem,

methodology, key findings, and conclusions. The abstract should be a concise

overview that provides enough information for readers to understand the study

without reading the full report.

3. Introduction

Background: Provide an in-depth review of the literature leading up to the research

question. Discuss relevant theories, key studies, and existing knowledge in the field.

Research Problem: Clearly state the research problem or question that the study

addresses.

Purpose: Restate the purpose of the study and why it is important.

Hypotheses or Research Questions: Reiterate the hypotheses or research questions

that guided the study.

Literature Review: Expand on the literature review presented in the proposal.

Include more detailed summaries of relevant research, discuss theoretical frameworks,

and identify gaps that your study aimed to fill.

4. Method

Participants: Provide a detailed description of the participants, including how they

were recruited, demographic information, and any relevant characteristics.

Materials/Instruments: Describe in detail the materials and instruments used in the

study. Include any modifications made to standard instruments and provide evidence

of reliability and validity where applicable.

25
 Procedure: Provide a comprehensive account of the procedures followed in the study.

This should include how participants were treated, the specific tasks they were asked

to perform, and any controls or conditions applied.

Design: Clearly explain the research design and the rationale behind it. Define the

independent and dependent variables and describe how they were manipulated or

measured.

5. Results

Data Analysis: Present the results of your data analysis. Use appropriate statistical

tests and report the results in APA format (e.g., t-test, ANOVA, regression analysis).

Include both descriptive statistics (e.g., means, standard deviations) and inferential

statistics (e.g., p-values, effect sizes).

Tables and Figures: Use tables and figures to visually represent your data. Each table

and figure should have a title and a number (e.g., Table 1, Figure 1) and should be

referred to in the text.

Text Presentation: Summarize the key findings in the text, providing context and

interpretation for the tables and figures. Avoid redundancy between the text and the

tables/figures.

Significance: Report the significance levels of your findings and indicate whether

your hypotheses were supported or not.

6. Discussion

Interpretation of Results: Discuss the results in the context of the research questions

or hypotheses. How do the findings contribute to the existing body of knowledge?

What do they suggest about the research problem?

26
 Comparison with Previous Research: Compare your results with previous studies.

Are they consistent with or different from what has been found before? Why might

this be the case?

Limitations: Acknowledge any limitations of the study, such as sample size,

methodology, or potential biases. Discuss how these limitations might affect the

interpretation of the results.

Implications: Consider the theoretical and practical implications of your findings.

How might they impact the field of study? What are the potential applications?

Conclusions: Summarize the main findings and their significance. Suggest directions

for future research based on your results.

7. References

Formatting: List all sources cited in your report using APA style. Ensure that all

citations in the text correspond to entries in the reference list.

Order: Arrange the references alphabetically by the last name of the first author.

Hanging Indent: Use a hanging indent format for each reference entry.

8. Appendices (if applicable)

Supplementary Material: Include any supplementary materials that were part of the

research but not essential to the main text, such as detailed statistical outputs,

additional tables, raw data, or copies of the survey instruments used.

27
 UNIT 2 EXPERIMENTAL RESEARCH DESIGNS AND SCALING

2.1 Important Concepts Relating To Research Design

Research design is the framework or blueprint for a research study that guides the

collection, measurement, and analysis of data.

1. Definition of Research Design

Research design is a strategic plan that outlines how a researcher intends to conduct the

study. It serves as a structured guide that ensures all aspects of the research process, from

data collection to analysis, are well-organized and coherent.

Gliner, Morgan, and Leech (2017) emphasize that a research design must address

the research questions or hypotheses, ensure the control of extraneous variables, and

guide the process of data collection and analysis.

Kothari (1985) describes research design as the conceptual structure within which

research is conducted. It constitutes the blueprint for the collection, measurement, and

analysis of data.

2. Types of Research Design

Research designs are broadly categorized based on the nature of the research and the type

of data collected. Each design type serves different research purposes.

1. Exploratory Research Design:

Used when the research problem is not well defined.

Kothari (1985) notes that exploratory research is primarily qualitative and

helps in understanding a problem, generating hypotheses, and guiding

subsequent research.

2. Descriptive Research Design:

28
 Focuses on describing the characteristics of a population or phenomenon.

Singh (2006) explains that descriptive research answers the "what" question,

providing detailed information about the subject without investigating

causality.

3. Experimental Research Design:

Seeks to establish cause-and-effect relationships.

Gliner, Morgan, and Leech (2017) highlight that in experimental research,

the researcher manipulates one or more independent variables to observe the

effect on a dependent variable. Randomization and control groups are essential

features of this design.

4. Correlational Research Design:

Examines the relationship between two or more variables without

manipulating them.

Howitt and Cramer (2020) clarify that while correlation indicates the

strength and direction of relationships, it does not imply causation.

5. Quasi-Experimental Design:

Similar to experimental designs but lacks random assignment.

Kerlinger (1994) points out that quasi-experimental designs are often used in

natural settings where randomization is not feasible. These designs attempt to

approximate the conditions of true experiments.

3. Validity in Research Design

29
Validity refers to the accuracy and trustworthiness of the study's results. Different types of

validity address different aspects of the research process.

1. Internal Validity:

The extent to which the observed effects in a study are due to the manipulation

of the independent variable and not other factors.

Kerlinger (1994) stresses that internal validity is achieved by controlling

extraneous variables and ensuring that the study's conditions are as close to the

intended experimental conditions as possible.

2. External Validity:

The extent to which the results of a study can be generalized to other

situations, people, settings, and times.

Singh (2006) points out that external validity is enhanced by using

representative samples and realistic settings in the research.

3. Construct Validity:

Refers to the degree to which a test or instrument measures the concept it is

intended to measure.

Howitt and Cramer (2020) explain that construct validity involves ensuring

that the operational definitions of variables truly reflect the theoretical

constructs.

4. Ecological Validity:

Refers to the extent to which research findings generalize to real-world

settings.

Gliner et al. (2017) suggest that studies conducted in natural settings tend to

have higher ecological validity compared to those conducted in artificial

laboratory environments.

30
4. Ethical Considerations in Research Design

Ethics play a crucial role in designing and conducting research. Researchers must ensure

that their study adheres to ethical guidelines to protect participants and maintain scientific

integrity.

1. Informed Consent:

Participants must be fully informed about the study's purpose, procedures,

risks, and benefits before agreeing to participate.

Howitt (2019) emphasizes that informed consent is a cornerstone of ethical

research, ensuring that participation is voluntary and based on a full

understanding of the study.

2. Confidentiality:

Researchers must protect the privacy of participants by keeping their data

confidential.

Kothari (1985) highlights the importance of maintaining confidentiality to

build trust with participants and encourage honest responses.

3. Protection from Harm:

Researchers are responsible for ensuring that participants are not exposed to

unnecessary risk or harm during the study.

Gliner et al. (2017) discuss the need for researchers to conduct a risk-benefit

analysis to ensure that the benefits of the research outweigh any potential risks

to participants.

5. Steps in Developing a Research Design

31
Developing a research design involves several steps that guide the research process from

start to finish.

1. Formulating the Research Problem:

Identifying and clearly defining the research problem is the first and most

critical step.

Singh (2006) explains that a well-defined problem guides the direction of the

research and determines the research questions or hypotheses.

2. Review of Literature:

Reviewing existing research helps identify gaps, refine the research problem,

and build on previous findings.

Howitt and Cramer (2020) suggest that a comprehensive literature review is

essential for understanding the current state of knowledge in the field and

positioning the study within that context.

3. Formulating Hypotheses:

Hypotheses are specific predictions derived from the research problem that

guide the study.

Zechmeister et al. (2001) emphasize that hypotheses should be clear, testable,

and based on theoretical or empirical grounds.

4. Determining the Research Design:

Choosing the appropriate research design depends on the nature of the

research problem, the research questions, and the type of data required.

Gliner et al. (2017) advise that the research design should align with the

study's objectives and ensure that the research questions can be answered

effectively.

5. Data Collection and Analysis:

32
 The researcher collects data according to the chosen method and analyzes it

using appropriate techniques.

Howitt (2019) highlights that data collection and analysis should be

systematic and aligned with the research design to ensure valid and reliable

results.

6. Challenges in Research Design

Research design can present several challenges that researchers must address to ensure

the validity and reliability of their study.

1. Selection Bias:

Occurs when the sample is not representative of the population, leading to

biased results.

Kothari (1985) notes that careful sampling design and randomization can help

mitigate selection bias.

2. Confounding Variables:

These are extraneous variables that can influence the outcome of the study,

potentially leading to incorrect conclusions.

Kerlinger (1994) advises that researchers should identify and control for

confounding variables to enhance the internal validity of the study.

3. Ethical Dilemmas:

Researchers may face ethical challenges such as managing conflicts of

interest, ensuring participant well-being, and maintaining objectivity.

Howitt (2019) discusses the importance of adhering to ethical guidelines and

seeking ethical approval from relevant bodies to address these dilemmas.

33
7. Importance of Research Design

A well-structured research design is crucial for the success of a study. It ensures that the

research process is systematic, that the data collected is reliable, and that the findings are

valid and generalizable.

Gliner, Morgan, and Leech (2017) emphasize that a strong research design enhances

the credibility of the study by providing a clear roadmap for addressing the research

questions.

Kothari (1985) adds that a carefully planned research design helps in minimizing

bias, controlling variables, and ensuring that the study's findings are robust and

replicable.

34
2.2 Basic Principles and Functions Of Experimental Designs

Experimental designs are fundamental to research in psychology and other sciences. They

allow researchers to investigate causal relationships between variables by systematically

manipulating one or more independent variables and observing the effects on dependent

variables.

1. Basic Principles of Experimental Designs

Control: Experimental designs aim to control extraneous variables that might

influence the outcome. This is achieved through random assignment, control groups,

and standardizing procedures.

Randomization: Random assignment of participants to different conditions or groups

helps ensure that any differences observed are due to the manipulation of the

independent variable rather than pre-existing differences between participants.

Manipulation: The researcher manipulates one or more independent variables to

observe their effect on dependent variables. This helps establish a causal relationship.

Replication: Repeating the experiment or conducting similar studies helps verify

findings and ensures that results are reliable and generalizable.

Validity: Experimental designs strive for high internal validity (the extent to which

the experiment accurately measures the effect of the independent variable) and

external validity (the extent to which findings can be generalized to other settings or

populations).

2. Functions of Experimental Designs

Establishing Causality: Experimental designs are particularly valuable for

establishing cause-and-effect relationships. By manipulating the independent

35
 variable and controlling for confounding factors, researchers can infer causal links

between variables.

Testing Hypotheses: Experimental designs allow researchers to test specific

hypotheses about how variables are related. This is done through structured

manipulation and measurement.

Control and Comparison: The use of control groups and comparison conditions

helps isolate the effects of the independent variable from other potential

influences.

Assessing Effects: Researchers can quantify the effects of different treatments or

interventions on the dependent variable, providing clear evidence of effectiveness

or impact.

Types of Experimental Designs

Between-Subjects Design: Participants are assigned to different groups, each

experiencing a different level of the independent variable. This design helps

compare the effects across groups.

Within-Subjects Design: The same participants are exposed to all levels of the

independent variable, allowing for comparisons within the same group.

Factorial Design: This design involves multiple independent variables, allowing

researchers to examine the interaction effects between variables.

Repeated Measures Design: Similar to the within-subjects design, but

specifically involves repeated observations of the same participants under

different conditions.

36
Randomized Controlled Trial (RCT): A rigorous experimental design where

participants are randomly assigned to either a treatment group or a control group,

commonly used in clinical research.

37
2.3 Between-group research designs

Between-group research designs, also known as between-subjects designs, are a

fundamental approach in experimental research. They involve comparing different groups

of participants, each exposed to different levels of the independent variable, to assess the

impact on the dependent variable.

1. Basic Concept

In a between-group design, participants are assigned to different groups, and each group

receives a different treatment or condition. The primary aim is to compare the effects of

these different conditions on the outcomes of interest.

2. Types of Between-Group Designs

Simple Experimental Design: Involves comparing two or more groups that

receive different treatments or conditions. For instance, one group might receive a

new educational intervention, while another group receives the standard

intervention.

Randomized Controlled Trial (RCT): A rigorous type of between-group design

where participants are randomly assigned to either the treatment group or the

control group. This method minimizes bias and ensures that any observed

differences are due to the treatment.

Matched Groups Design: Participants are matched on certain characteristics

(e.g., age, gender) and then randomly assigned to different groups. This helps

control for potential confounding variables by ensuring that groups are equivalent

at the start of the experiment.

38
 Factorial Design: A type of between-group design involving two or more

independent variables. It allows researchers to examine the main effects of each

independent variable and their interaction effects on the dependent variable.

3. Advantages of Between-Group Designs

Control Over Variables: By comparing different groups, researchers can control

for variables that might affect the outcome, thus isolating the effects of the

independent variable.

Clear Comparison: This design provides a clear comparison between different

conditions or treatments, making it easier to assess the impact of the independent

variable.

Reduces Order Effects: Since different participants are used for each condition,

order effects (e.g., practice or fatigue) that can occur in within-subjects designs are

minimized.

4. Disadvantages of Between-Group Designs

Increased Variability: Differences between groups can introduce variability,

which might obscure the effects of the independent variable. Random assignment

helps mitigate this issue but may not eliminate it entirely.

Requires More Participants: To ensure reliable results, between-group designs

often require larger sample sizes compared to within-subjects designs because

each participant is only exposed to one condition.

Potential for Group Differences: Even with random assignment, there may be

differences between groups that are not related to the independent variable but still

affect the outcome.

39
5. Key Concepts and Terminology

Control Group: A group that does not receive the experimental treatment or

intervention. It is used as a baseline to compare the effects of the treatment.

Experimental Group: The group that receives the treatment or intervention being

tested.

Random Assignment: The process of assigning participants to different groups in

a way that ensures each participant has an equal chance of being placed in any

group. This helps control for confounding variables.

Between-Group Comparison: The process of comparing outcomes between

different groups to assess the effects of the independent variable.

40
2.4 Within-group designs

Within-group designs, also known as within-subjects designs, involve using the same

participants across all conditions or treatments in an experiment. This approach allows

researchers to assess the effects of different conditions on the same group of participants,

providing a direct comparison of responses under different experimental conditions.

1. Basic Concept

In a within-group design, each participant is exposed to all levels of the independent

variable. The dependent variable is measured multiple times for each participant under

different conditions, enabling comparisons within the same individual.

2. Types of Within-Group Designs

Repeated Measures Design: The same participants are tested repeatedly under different

conditions or at different time points. This design helps in comparing the effects of

various conditions directly within each participant.

Cross-Over Design: Participants are exposed to all conditions in a specific sequence,

with a washout period in between to avoid carryover effects. This design allows each

participant to serve as their own control, improving the precision of comparisons.

Longitudinal Design: A type of repeated measures design where participants are assessed

multiple times over an extended period. This approach is useful for studying changes over

time and developmental processes.

3. Advantages of Within-Group Designs

Control of Individual Differences: Since the same participants are used across all

conditions, individual differences (e.g., age, intelligence) are controlled. This reduces

41
variability related to these differences and enhances the ability to detect effects of the

independent variable.

Increased Statistical Power: Within-group designs generally require fewer participants

to achieve the same level of statistical power as between-group designs because the

variability between participants is minimized.

Efficient Use of Participants: Each participant provides data for all conditions, making

the design more efficient in terms of sample size and resources.

4. Disadvantages of Within-Group Designs

Order Effects: Repeated exposure to different conditions can lead to order effects, such

as practice effects, fatigue, or carryover effects from one condition to another.

Counterbalancing (e.g., varying the order of conditions) can help mitigate these effects.

Attrition: Participants dropping out of the study can impact the results, especially if

dropouts are not evenly distributed across conditions.

Complexity in Analysis: Analyzing data from within-group designs can be more

complex due to the need to account for repeated measures and potential correlations

between measurements.

5. Key Concepts and Terminology

Counterbalancing: A technique used to control for order effects by varying the order in

which participants experience different conditions. This helps ensure that any effects

observed are not due to the order of conditions.

Washout Period: In cross-over designs, a period between conditions where participants

are not exposed to the treatment or intervention, allowing any effects from the previous

condition to dissipate.

42
Carryover Effects: Effects of a previous condition that persist and influence the

participant's response to subsequent conditions. Counterbalancing and washout periods

are strategies to address these effects.

Practice Effects: Improvements in performance due to repeated exposure to the test or

task, rather than the treatment effect. Practice effects can be minimized through

appropriate design and counterbalancing.

43
2.5. Scaling: Psychophysical, Psychological

Scaling is a method used in research to measure and quantify variables that are otherwise

subjective or abstract. It involves translating qualitative observations into numerical data.

Understanding the principles and applications of psychophysical and psychological

scaling is essential for designing robust research studies and accurately interpreting data.

1. Psychophysical Scaling

Psychophysical scaling involves measuring the relationship between physical properties

of stimuli and the corresponding perceptions or sensations they produce. It is concerned

with how changes in physical stimuli (such as brightness, weight, or sound) affect our

sensory experiences.

Main Concepts

1. Absolute Threshold:

The minimum intensity of a stimulus that can be detected by an individual.

Example: The faintest sound that a person can hear in a quiet environment.

Measurement: Typically measured using methods like the method of limits,

method of constant stimuli, or method of adjustment.

2. Difference Threshold (Just Noticeable Difference, JND):

The smallest detectable difference between two stimuli that can be perceived.

Example: The minimum change in weight needed for a person to notice that a

weight has been added or removed.

Measurement: Can be assessed using methods such as the Weber-Fechner

law, which quantifies how differences in stimuli relate to perceptual

differences.

44
3. Fechner's Law:

States that the perceived intensity of a stimulus is a logarithmic function of its

actual intensity. As stimulus intensity increases, the perceived change in

intensity becomes progressively smaller.

Mathematical Representation: S=k⋅log⁡(I)S = k \cdot \log(I)S=k⋅log(I),

where SSS is the perceived intensity, III is the actual intensity, and kkk is a

constant.

Application: Used to model sensory experiences like light and sound

intensity.

4. Stevens' Power Law:

Suggests that the perceived magnitude of a stimulus is a power function of its

actual intensity, providing a more flexible model than Fechner's Law.

Mathematical Representation: P=k⋅IaP = k \cdot I^aP=k⋅Ia, where PPP is

the perceived magnitude, III is the stimulus intensity, aaa is an exponent, and

kkk is a constant.

Application: Applicable across a broader range of sensory modalities,

including touch and taste.

Applications

 Psychophysics Experiments: Used to determine thresholds and scaling functions,

such as assessing sensory discrimination or the impact of stimulus intensity on

perception.

45
 Development of Measurement Scales: Helps in designing scales that reflect how

changes in stimulus intensity are perceived by individuals, such as pain scales or

visual acuity tests.

2. Psychological Scaling

Psychological scaling involves measuring psychological attributes, such as attitudes,

opinions, and personality traits. It aims to quantify abstract constructs and translate them

into numerical data that can be analyzed statistically.

Main Concepts

1. Likert Scale:

A scale used to measure attitudes or opinions by asking respondents to rate

their level of agreement or disagreement with a series of statements.

Format: Typically a 5-point or 7-point scale ranging from "Strongly

Disagree" to "Strongly Agree."

Application: Widely used in surveys and questionnaires to capture subjective

opinions and attitudes.

2. Semantic Differential Scale:

Measures the meaning of concepts or objects along a set of bipolar adjectives

(e.g., good-bad, strong-weak).

Format: Respondents rate concepts on a scale between two opposing

adjectives.

Application: Useful for assessing the connotative meaning of concepts or

products.

46
3. Thurstone Scale:

Measures attitudes by presenting a series of statements about a particular

topic. Judges evaluate these statements for favorability, and each statement is

assigned a numerical value.

Format: Statements are aggregated to assess the overall attitude of

respondents.

Application: Often used to measure complex attitudes and beliefs.

4. Guttman Scale:

Measures the degree to which respondents agree with a series of progressively

more extreme statements on a particular topic.

Format: Respondents who agree with a more extreme statement are assumed

to agree with less extreme ones.

Application: Useful for measuring cumulative attitudes or behaviors.

Applications

Survey Research: Utilized in designing surveys and questionnaires to capture

data on psychological constructs such as attitudes, opinions, and personality

traits.

Attitude Measurement: Helps in understanding and quantifying attitudes,

beliefs, and perceptions.

Personality Assessment: Assists in evaluating personality traits and behaviors

through structured scales.

47
 UNIT 3 QUASI-EXPERIMENTAL DESIGNS AND MUTLIVARIATE

RESEARCH

3.1. Single-case designs and small-n research

Single-case designs and small-N research are methodologies used in psychology and

behavioral sciences to study the effects of an intervention or phenomena in one or a few

subjects. These approaches are particularly useful in applied settings such as clinical

psychology, education, and organizational behavior, where large samples may not be

available or the focus is on individual cases.

1. Introduction to Single-Case Designs and Small-N Research

Single-Case Design: A single-case design (SCD) involves the in-depth study of a

single subject (an individual or a specific unit, such as a classroom). The primary goal

is to observe how a subject responds to a treatment or intervention over time, with the

subject often serving as their own control. This design allows researchers to draw

conclusions about the effectiveness of interventions on a case-by-case basis.

Small-N Research: According to Howitt and Cramer (2020), small-N research

focuses on a small number of subjects, typically fewer than ten. This approach is

designed to provide rich, detailed insights into the behaviors, experiences, or

phenomena under investigation. Small-N research often emphasizes qualitative

methods, although quantitative methods can also be employed.

2. Types of Single-Case Designs

 AB Design:

Structure: The AB design is the most basic single-case design. It consists of

two phases: A (baseline) and B (intervention). During the baseline phase, the

subject's behavior is observed without any intervention to establish a standard

48
 for comparison. In the intervention phase, a treatment is introduced, and any

changes in the subject's behavior are monitored.

Application: This design is commonly used in clinical settings to assess the

impact of therapies or behavioral interventions. For example, it might be used

to evaluate how a new therapy affects a patient’s anxiety levels (Gliner et al.,

2017).

Limitations: The AB design is susceptible to threats to internal validity, such

as history or maturation effects, which can confound the results (Kerlinger,

1994).

 ABA and ABAB Designs:

Structure: The ABA design is an extension of the AB design, adding a second

baseline phase (A) after the intervention. The ABAB design further adds a

second intervention phase (B). These designs allow for a more rigorous

assessment of the intervention's effects by observing whether changes in

behavior reverse when the intervention is withdrawn and whether they reoccur

when the intervention is reintroduced.

Application: ABA and ABAB designs are useful for demonstrating the

causality of an intervention, such as in behavioral modification programs for

children with autism (Kerlinger, 1994).

Advantages: These designs help to rule out confounding variables and

increase the reliability of the findings.

Challenges: Ethical concerns may arise if the withdrawal of a beneficial

intervention is harmful to the subject.

 Multiple Baseline Design:

49
 Structure: In this design, the intervention is applied across multiple baselines,

such as different subjects, behaviors, or settings, at different points in time.

The staggered introduction of the intervention helps establish a causal

relationship between the intervention and the observed effects.

Application: This design is often used in educational research to evaluate

interventions across different classrooms or students (Kothari, 1985).

Strengths: It avoids the ethical issue of withdrawing an intervention, making

it a preferred choice when the intervention has a significant positive impact.

 Alternating Treatments Design:

Structure: This design allows researchers to compare the effects of two or

more treatments by rapidly alternating them within the same subject. The

effects of each treatment are measured independently.

Application: This design is suitable for evaluating which of two or more

treatments is most effective for a particular individual, such as comparing

different teaching methods (Singh, 2006).

Benefits: It enables a direct comparison between interventions without

needing a withdrawal phase.

Drawbacks: The rapid alternation of treatments may cause confusion or

carryover effects, complicating the interpretation of results.

3. Strengths of Single-Case Designs

 In-Depth Analysis: Single-case designs allow for a detailed examination of the

individual subject’s behavior, offering insights that might be obscured in large-group

studies (Gliner et al., 2017).

50
 Individualized Interventions: These designs are particularly valuable in clinical

settings, where treatments can be tailored to the specific needs and circumstances of

the patient (Howitt, 2019).

 Flexibility and Adaptability: Researchers can modify the intervention based on

ongoing results, making these designs highly flexible and adaptive to real-world

conditions (Zechmeister et al., 2001).

 Useful in Rare or Unique Cases: Single-case designs are ideal for studying rare

conditions or unique cases where large samples are not available (Gliner et al., 2017).

4. Challenges and Limitations

 Limited Generalizability: One of the most significant limitations of single-case

designs is the difficulty in generalizing findings to larger populations. The results are

specific to the individual case and may not apply to others (Singh, 2006).

 Potential for Bias: The close interaction between the researcher and the subject can

introduce bias, particularly if the researcher has expectations about the outcome

(Gliner et al., 2017).

 Difficulty in Controlling Extraneous Variables: Controlling all external variables

that might affect the outcome is challenging in single-case designs, potentially

confounding the results (Kothari, 1985).

5. Small-N Research

 Focus on Qualitative Methods: Small-N research often employs qualitative methods,

such as in-depth interviews, case studies, and thematic analysis. This approach allows

for a comprehensive exploration of the subject matter, focusing on the richness of the

data rather than its generalizability (Howitt & Cramer, 2020).

51
 Exploratory and Descriptive: Small-N research is particularly valuable in

exploratory studies where the goal is to understand new or poorly understood

phenomena. It is often used to generate hypotheses that can be tested in larger studies

(Gliner et al., 2017).

 Application in Applied Settings: Small-N research is frequently used in applied

settings where large samples are not feasible or necessary, such as in the study of

specific psychological disorders or educational interventions (Zechmeister et al.,

2001).

6. Ethical Considerations

 Informed Consent: Ensuring informed consent is crucial, especially in single-case

and small-N research where the focus on individual cases may increase the risk of

identifying the subject (Howitt, 2019).

 Confidentiality: Maintaining the confidentiality of data is particularly important in

single-case designs, as the specific focus on one subject makes it easier to identify

them (Gliner et al., 2017).

7. Applications and Importance

 Clinical Psychology: Single-case designs are extensively used in clinical psychology

to evaluate the effectiveness of therapeutic interventions on individual patients. For

example, a therapist might use an ABAB design to assess the impact of cognitive-

behavioral therapy on a patient’s depression (Kerlinger, 1994).

 Education: In educational psychology, these designs are used to tailor instructional

methods to individual students, allowing for the assessment of interventions like

positive reinforcement in improving student behavior (Kothari, 1985).

52
 Organizational Behavior: Single-case and small-N designs are also valuable in

organizational behavior research, where they can be used to study the effects of

interventions like training programs on employee performance (Singh, 2006).

3.2. Quasi-experimental designs: Non-equivalent Control Group Designs,

Regression-

Discontinuity designs, Cohort designs, Time Series designs

Quasi-experimental designs are powerful tools in research, especially when

randomization is not possible due to practical or ethical constraints. These designs allow

researchers to study the effects of an intervention or treatment by comparing groups that

are not randomly assigned, making them useful in real-world settings like education,

healthcare, and organizational studies.

1. Non-Equivalent Control Group Designs

In non-equivalent control group designs, there are two or more groups that receive

different treatments or no treatment at all. However, the groups are not randomly

assigned, which may lead to differences in group characteristics other than the

treatment.

Characteristics:

Pre-Test and Post-Test: Often, both groups are measured on the outcome variable

before and after the intervention. This helps in assessing the changes attributable to

the treatment.

A major concern in this design is selection bias, as the groups may differ on various

factors (e.g., motivation, prior knowledge) that can influence the outcome.

53
Example:

Suppose researchers want to evaluate a new teaching method. They might compare

the performance of students in two different classes, where one class uses the new

method and the other continues with the traditional method. Since the classes were

pre-existing, the groups are not equivalent at the outset.

Advantages:

 Feasibility in real-world settings.

 Allows for the study of interventions in natural environments.

Limitations:

 Potential for confounding variables.

 Difficulty in establishing causal relationships due to selection bias.

2. Regression-Discontinuity Designs

Regression-discontinuity design is a quasi-experimental approach where participants

are assigned to treatment and control groups based on a cutoff score on a continuous

pre-treatment measure (e.g., test scores, income level).

Characteristics:

Assignment Based on Cutoff: Individuals scoring above or below a predetermined

threshold are assigned to different groups.

Sharp Discontinuity: The key assumption is that the only difference between those

just above and just below the cutoff is the treatment, allowing for causal inference.

Example:

Imagine a scholarship program where students with test scores above a certain

threshold receive financial aid. Researchers could compare the academic performance

54
 of students just above and just below the cutoff to assess the impact of the

scholarship.

3. Cohort Designs

In cohort designs, researchers follow a group (cohort) of individuals who share a

common characteristic or experience over time to assess the effects of an intervention

or exposure.

Characteristics:

Longitudinal Tracking: Cohorts are often tracked over a period of time to observe

changes and outcomes.

Comparison Across Cohorts: Different cohorts may be exposed to different levels of

an independent variable, or a single cohort may be observed before and after an

intervention.

Example:

Researchers might study the health outcomes of individuals who were exposed to a

particular environmental factor during a specific period, comparing them to a cohort

4. Time Series Designs

Time series designs involve repeated measurements of the same group over time

before and after an intervention. The design helps in identifying trends and changes

that can be attributed to the intervention.

Characteristics:

Multiple Observations: The key feature is the collection of data at multiple points

before and after the intervention.

55
 Interruption Analysis: Researchers analyze whether there is a noticeable

'interruption' or change in the trend following the intervention.

Example:

A city might implement a new traffic law, and researchers could analyze traffic

accident rates over several months before and after the law was implemented to assess

its impact.

56
3.3. Multivariate techniques: Multiple regression, multivariate analysis of variance,

Path Analysis, Structural Equation Modelling (SEM)

Multivariate Techniques: Detailed Explanation

Multivariate techniques are essential in research as they allow the analysis of multiple

variables simultaneously, helping researchers understand complex relationships and

interactions.

1. Multiple Regression

Concept:

Multiple regression is an extension of simple linear regression that predicts the value of a

dependent variable based on the values of two or more independent variables. The goal is

to model the relationship between a single outcome and several predictors.

Application: For example, predicting academic performance (Y) based on hours of

study (X1), class attendance (X2), and prior knowledge (X3).

Importance:

 Interpretation: The coefficients (β\betaβ) indicate the change in the dependent

variable for a one-unit change in the predictor, holding all other variables constant.

 Usefulness: It helps in understanding the relative importance of different predictors

and controlling for confounding variables.

2. Multivariate Analysis of Variance (MANOVA)

Concept:

MANOVA extends the Analysis of Variance (ANOVA) by examining the influence of

independent variables on multiple dependent variables simultaneously. It is used when

57
 researchers are interested in understanding how different groups differ across several

outcome measures.

Multivariate normality, homogeneity of variance-covariance matrices, and linear

relationships between dependent variables.

Application: For example, assessing the effect of different teaching methods

(independent variable) on students' scores in math, science, and language (dependent

variables).

Importance:

Interpretation: MANOVA assesses whether the mean vectors of the dependent

variables are significantly different across groups.

Usefulness: It is powerful for detecting differences when dependent variables are

correlated, providing a more holistic view of the data.

3. Path Analysis

Concept:

Path analysis is a specialized form of multiple regression used to examine causal

relationships between variables. It extends regression by allowing for the analysis of

direct, indirect, and total effects in a model.

Key Features:

Model: Represents a system of regression equations that describe the relationships

between observed variables.

Path Diagram: A visual representation of the hypothesized relationships, with arrows

indicating the direction and strength of the effects.

58
 Application: Used to model the relationships between variables like socioeconomic

status, education, and job performance.

Importance:

Interpretation: Path coefficients indicate the strength of the relationships, with direct

paths representing direct effects and indirect paths representing mediated effects.

Usefulness: Helps in understanding complex causal mechanisms and testing

theoretical models.

4. Structural Equation Modeling (SEM)

Concept:

SEM is an advanced multivariate technique that combines factor analysis and path

analysis to assess complex models involving latent (unobserved) variables and observed

variables. SEM is used to test hypotheses about relationships among variables, both

directly and indirectly.

Key Features:

 Model: SEM consists of two parts: the measurement model (which specifies the

relationships between latent variables and their indicators) and the structural model

(which specifies the relationships between latent variables).

 Diagram: SEM is often represented visually using a path diagram that shows both

measurement and structural relationships.

 Application: Used in psychological research to test theories that involve multiple

interrelated variables, such as the relationships between personality traits, stress, and

health outcomes.

Importance:

59
 Interpretation: SEM provides a comprehensive framework for testing complex

models, including the estimation of direct, indirect, and total effects, as well as model

fit indices.

 Usefulness: It is highly flexible and can accommodate a wide range of research

designs and data types, making it invaluable for theory testing.

60
3.4. Factor analysis: Basic terms, overview of extraction methods, Overview of

rotation Methods

Basic Terms in Factor Analysis

1. Factor:

A latent variable that cannot be directly observed but is inferred from the

observed variables. It represents an underlying dimension that explains

patterns in the data.

Example: In psychological research, a factor might represent a construct like

"emotional intelligence" inferred from several related test items.

2. Variable:

An observable measure or item used in the analysis. Each variable is a data

point used to understand the relationships between factors.

Example: Survey responses to questions about job satisfaction are variables

that might be used to identify underlying factors of job satisfaction.

3. Loadings:

The correlation coefficients between variables and factors. They indicate how

much a factor contributes to explaining a variable.

Example: If a variable like "employee motivation" has a high loading on a

factor, it means that the factor strongly influences that variable.

4. Eigenvalue:

Represents the total variance in the data accounted for by a factor. A higher

eigenvalue means that the factor explains more of the variance.

Example: A factor with an eigenvalue of 3 explains three times more variance

than a factor with an eigenvalue of 1.

5. Communality:

61
 The proportion of each variable’s variance that is shared with other variables,

explained by the factors. It shows how well a variable is accounted for by the

extracted factors.

Example: If a variable has a communality of 0.80, it means 80% of the

variance in that variable is explained by the factors.

6. Factor Score:

A score that represents an individual’s position on a particular factor. It is

calculated based on the individual’s scores on the observed variables and the

factor loadings.

Example: A factor score for "leadership ability" might be computed for each

participant based on their responses to leadership-related questions.

Extraction Methods

1. Principal Component Analysis (PCA):

PCA is used to reduce the dimensionality of the data by transforming the

original variables into a smaller set of uncorrelated components (principal

components). It focuses on explaining as much variance as possible with fewer

components.

Procedure:

1. Compute the Correlation Matrix: Analyze the correlations among

the variables.

2. Extract Components: Use eigenvalues and eigenvectors to extract

components. Components are ranked by the amount of variance they

explain.

3. Select Components: Decide how many components to retain based on

criteria like the eigenvalue greater than 1 rule.

62
2. Common Factor Analysis:

To identify underlying factors that account for the observed correlations

among variables, focusing on shared variance rather than total variance.

Procedure:

1. Extract Factors: Use methods like principal axis factoring to extract

factors.

2. Communalities: Estimate the proportion of variance in each variable

explained by the factors.

3. Factor Rotation: Apply rotation to improve interpretability.

3. Maximum Likelihood Extraction:

To estimate factor models by maximizing the likelihood function. This method

provides estimates that are statistically efficient under the assumption of

normally distributed data.

Procedure:

1. Model Specification: Specify the factor model.

2. Estimate Parameters: Use statistical software to maximize the

likelihood function.

3. Assess Fit: Evaluate how well the model fits the data.

Rotation Methods

1. Varimax Rotation:

To simplify the factor structure by maximizing the variance of squared

loadings of each factor. It aims to make factors as interpretable as possible by

ensuring that each variable loads highly on one factor and minimally on

others.

Procedure:

63
 1. Orthogonal Rotation: Keeps factors uncorrelated.

2. Adjust Loadings: Rotate the factors to achieve a simple structure

where each variable has a high loading on one factor and low loadings

on others.

2. Promax Rotation:

To allow factors to be correlated, which can sometimes provide a more

accurate representation of the data if factors are not truly independent.

Procedure:

1. Oblique Rotation: Permits factors to correlate.

2. Adjust Loadings: After an initial orthogonal rotation, rotate the

factors to achieve a simpler structure with correlated factors.

64
3.5 Higher order factor analysis

What is Higher-Order Factor Analysis?

Higher-order factor analysis is an extension of factor analysis used to understand

hierarchical relationships among factors. While basic factor analysis identifies underlying

factors that explain the correlations among observed variables, higher-order factor

analysis takes this a step further by examining whether these factors themselves can be

further explained by more general, overarching factors.

Steps in Higher-Order Factor Analysis

1. Conducting First-Order Factor Analysis:

Data Collection: Gather data on a set of observed variables (e.g., responses to

psychological test items).

Extraction of Factors: Use techniques like Principal Component Analysis

(PCA) or Exploratory Factor Analysis (EFA) to identify the first-order factors.

These are the underlying dimensions that account for the correlations among

the observed variables.

Factor Rotation: Apply rotation methods (e.g., Varimax, Oblimin) to make

the factor structure more interpretable, ensuring that factors are clearly

defined.

Example: Suppose you have a psychological questionnaire with items designed to

measure traits such as anxiety, depression, and stress. After performing a first-order factor

analysis, you might identify factors like "Anxiety," "Depression," and "Stress" based on

the items' loadings.

2. Conducting Second-Order Factor Analysis:

65
 Using First-Order Factors as Variables: Treat the factors obtained from the

first-order factor analysis as the new set of variables. The goal is to investigate

whether these factors are influenced by higher-order factors.

Extraction of Second-Order Factors: Apply factor analysis techniques again

to the first-order factors to identify higher-order factors that may underlie

them. This analysis can reveal overarching constructs that explain the

relationships among the first-order factors.

Example: Continuing from the previous example, you might find that the first-order

factors "Anxiety," "Depression," and "Stress" are all related to a higher-order factor like

"Emotional Distress."

Key Concepts and Techniques

1. Factor Extraction:

Principal Component Analysis (PCA): Used for extracting factors based on

variance explained. PCA can be the first step in identifying initial factors

before applying higher-order factor analysis.

Common Factor Analysis: Focuses on the shared variance among variables,

which is crucial for understanding the underlying dimensions.

2. Factor Rotation:

Orthogonal Rotation (e.g., Varimax): Assumes factors are uncorrelated. It

simplifies interpretation by maximizing high loadings on each factor while

minimizing cross-loadings.

Oblique Rotation (e.g., Oblimin): Allows for correlated factors, which may

be more realistic for psychological constructs where factors often interrelate.

3. Model Fit and Validation:

66
 Confirmatory Factor Analysis (CFA): Used to validate the factor structure

obtained from exploratory analyses. It assesses how well the model fits the

data.

Goodness-of-Fit Indices: Include measures like the Chi-Square statistic,

Comparative Fit Index (CFI), and Root Mean Square Error of Approximation

(RMSEA).

Application in Research

Higher-order factor analysis is particularly useful in complex psychological research

where constructs are believed to be hierarchical or multidimensional. It helps in:

Understanding Complex Constructs: For instance, in personality psychology,

higher-order factors might help explain how various traits (like "Openness" and

"Conscientiousness") relate to more abstract constructs (like "Overall Personality

Structure").

Developing Measurement Instruments: It aids in refining and validating

psychological tests by understanding how different scales or subscales relate to

broader constructs.

67
 UNIT 4 QUALITATIVE RESEARCH: INTRODUCTION, PROCESS

AND ANALYSIS

4.1 Definition and scope of qualitative research

Qualitative research is a systematic method of inquiry that aims to explore and

understand human behavior, experiences, and the meaning individuals or groups attribute

to social phenomena. Unlike quantitative research, which focuses on numerical data and

statistical analysis, qualitative research emphasizes in-depth exploration of the how and

why behind human behavior and social processes.

According to Gliner, Morgan, and Leech (2017), qualitative research involves

collecting and analyzing non-numerical data to understand concepts, opinions, or

experiences. This approach is flexible and adaptive, allowing researchers to delve deeper

into the context and complexities of human interactions and behaviors.

Howitt (2019) adds that qualitative methods in psychology help researchers explore

subjective experiences, emotions, and underlying motivations that are difficult to

quantify. It is particularly effective in understanding individual or group perceptions and

behaviors in their natural environments, allowing for the rich, detailed exploration of

topics.

Scope of Qualitative Research

Qualitative research has a broad scope, extending across various fields such as

psychology, sociology, education, healthcare, and more. Its flexibility allows researchers

to study diverse topics ranging from personal experiences to social structures. Below are

key areas where qualitative research holds significance, supported by the references you

provided:

68
1. Exploring Complex Human Behaviors and Emotions

According to Howitt and Cramer (2020), qualitative methods are

indispensable for exploring the intricate dimensions of human emotions,

relationships, and behaviors that are difficult to measure quantitatively.

Qualitative research methods like in-depth interviews and participant

observation enable researchers to uncover hidden motivations, feelings, and

perceptions.

Example: Understanding how individuals cope with grief can involve qualitative

interviews to explore their emotional journey and personal experiences.

2. Studying Contextual Influences on Behavior

As outlined in Kerlinger (1994), qualitative research is particularly useful for

studying the influence of context on human behavior. It allows researchers to

examine how social, cultural, and environmental factors shape individual and

group behaviors.

Example: In a study exploring cultural attitudes toward mental health, qualitative

methods can provide deep insights into how social norms and traditions influence

perceptions of mental illness.

3. Developing New Theories and Concepts

Gliner, Morgan, and Leech (2017) emphasize that qualitative research is

often exploratory and contributes to theory development. Grounded theory, for

instance, is a qualitative method that develops new theories based on the data

collected rather than testing pre-existing hypotheses.

Example: Researchers studying leadership styles may use qualitative data to develop new

theories on effective leadership in modern workplaces.

4. Understanding Subjective Experiences

69
 Kothari (1985) highlights the importance of understanding individuals’ lived

experiences through qualitative research. This approach helps researchers

capture the personal, subjective views of participants, which quantitative data

often fail to address.

Example: Qualitative research can be used to explore the experiences of caregivers

looking after patients with Alzheimer's disease, offering insights into emotional

challenges and coping strategies.

5. Analyzing Social and Cultural Phenomena

Singh (2006) discusses the role of qualitative methods in understanding social

and cultural phenomena. These methods allow for the examination of how

cultural beliefs, practices, and social structures impact individual behavior and

group dynamics.

Example: A qualitative study might investigate how different cultural groups perceive

and practice gender roles in the workplace.

6. Evaluating Policies and Programs

According to Zechmeister, Zechmeister, and Shaughnessy (2001),

qualitative research is often employed in program evaluation to understand

how policies or interventions are implemented in real-world settings. It

provides detailed feedback from participants, stakeholders, and beneficiaries,

helping refine and improve the program.

Example: A qualitative evaluation of an educational reform initiative might explore

teachers' and students' experiences and perceptions, offering insights for future policy

adjustments.

70
4.2 Qualitative data Collection methods: Qualitative Interviewing, Focus groups,

Ethnography, Participant Observation

Qualitative data collection methods aim to gather rich, in-depth information about

human experiences, behaviors, and social phenomena. These methods prioritize

understanding context, individual perspectives, and the complexities of social

interactions. Below is a detailed explanation of some widely used qualitative data

collection methods, including qualitative interviewing, focus groups, ethnography, and

participant observation, supported by the provided references.

1. Qualitative Interviewing

Qualitative interviewing involves conducting one-on-one conversations with

participants to gather detailed, in-depth insights into their experiences, beliefs, and

perceptions. Unlike structured interviews used in quantitative research, qualitative

interviews are often semi-structured or unstructured, allowing for more flexibility and

responsiveness during the conversation.

Purpose and Use

 Gliner, Morgan, and Leech (2017) describe qualitative interviews as a primary tool

for understanding how individuals make sense of their experiences in natural settings.

This method is particularly useful when researchers seek to explore subjective

experiences and uncover underlying motivations, thoughts, or feelings.

 Howitt and Cramer (2020) highlight that interviews allow the researcher to delve

into topics that may not emerge in other forms of data collection, such as personal life

stories or detailed emotional responses.

Types

 Structured Interviews: Pre-determined questions are asked in a fixed order.

71
 Semi-Structured Interviews: The interviewer follows a guide but can deviate and

ask follow-up questions to explore interesting or unexpected responses.

 Unstructured Interviews: The interviewer has a broad topic or area of interest but

allows the conversation to flow freely based on the participant’s responses.

An in-depth interview with individuals experiencing workplace stress could reveal not

just the sources of stress but also the personal coping mechanisms and emotional impact

that may not be captured through surveys.

2. Focus Groups

A focus group is a data collection method that involves a small group of participants

(usually 6-12) discussing a specific topic under the guidance of a moderator. The goal is

to gather multiple perspectives on the subject of interest through group interaction.

Purpose and Use

 Gliner et al. (2017) emphasize that focus groups are valuable for exploring collective

opinions, group dynamics, and shared experiences, particularly when studying social

or cultural phenomena.

 Howitt (2019) explains that focus groups can reveal how social context and peer

influence shape opinions and behaviors, providing insights into the negotiation of

meaning within a group setting.

Advantages

 Diversity of perspectives: Group discussions allow researchers to capture a variety of

viewpoints in a single session.

 Interactive feedback: Participants can build on each other’s ideas, leading to richer

data.

72
 Natural group context: The social interaction within the group mirrors real-world

interactions.

Example

A focus group discussing attitudes towards mental health interventions could reveal not

only individual opinions but also how group members influence each other’s views,

highlighting the role of social dynamics.

3. Ethnography

Ethnography is a qualitative research method derived from anthropology, where

researchers immerse themselves in the natural environment of the participants to observe

and document their behaviors, cultures, and social interactions over an extended period of

time.

Purpose and Use

 Kerlinger (1994) describes ethnography as a holistic approach to understanding how

people live, behave, and interact within their cultural contexts. The goal is to capture a

detailed, nuanced understanding of social life.

 Howitt and Cramer (2020) note that ethnography is particularly useful in studies of

organizational behavior, community practices, or cultural rituals where the researcher

needs to observe the dynamics firsthand.

Data Collection in Ethnography

 Ethnographic data collection often involves participant observation, informal

interviews, and document analysis.

 Researchers may spend months or even years in the field, becoming part of the social

group to gain deeper insights into its practices and meanings.

Example

73
An ethnographic study of a remote village’s healthcare practices would involve the

researcher living in the community, observing day-to-day health-related activities, and

engaging with locals to understand their perspectives on health and healing.

4. Participant Observation

Participant observation is a method in which the researcher becomes part of the group

or community they are studying. While observing the group’s behaviors and interactions,

the researcher also engages in the activities to gain a deeper understanding of the group’s

practices.

Purpose and Use

 Kothari (1985) and Singh (2006) discuss participant observation as an immersive

method that allows researchers to directly experience the setting or phenomenon

under study. This method enables the researcher to collect data on both overt

behaviors and subtle, non-verbal cues that may not be captured through interviews or

surveys.

 Gliner et al. (2017) highlight that participant observation is particularly valuable

when the researcher aims to understand the cultural norms, rituals, or everyday

practices of a particular group.

Roles of the Researcher

 Complete Participant: Fully engages in the group’s activities without revealing their

role as a researcher.

 Participant-as-Observer: The researcher is known to the group but actively

participates in its activities.

 Observer-as-Participant: The researcher primarily observes but occasionally

interacts with the group.

74
Example

A researcher studying street vendors’ interactions with customers might engage in selling

goods alongside them, participating in the daily routines to better understand the business

culture and challenges faced by the vendors.

75
4.3 Qualitative data Analysis 1: Data Transcription method, Thematic Analysis,

Grounded theory, Social constructionist discourse Analysis

Qualitative data analysis involves systematically organizing and interpreting non-

numerical data to identify patterns, themes, and meanings. Several techniques are used to

analyze qualitative data, including Data Transcription, Thematic Analysis, Grounded

Theory, and Social Constructionist Discourse Analysis. Below is a detailed explanation

of each method, supported by the provided references.

1. Data Transcription Method

Data transcription is the process of converting audio or video recordings from

interviews, focus groups, or observations into written text. This is often the first step in

qualitative data analysis, as it enables the researcher to closely engage with the data by

reading and interpreting the dialogue or actions.

Purpose and Use

 Howitt (2019) describes transcription as crucial in preparing qualitative data for

detailed analysis. The accuracy and fidelity of the transcription are essential, as subtle

non-verbal cues (e.g., pauses, tone, emphasis) are often important in interpreting

qualitative data.

 Gliner, Morgan, and Leech (2017) highlight that transcription allows for a deeper

immersion in the data, aiding researchers in identifying patterns and recurring themes.

Approaches to Transcription

 Verbatim Transcription: Involves capturing every spoken word and sound exactly as

heard, including non-verbal cues such as laughter or pauses.

 Intelligent Verbatim Transcription: Focuses on capturing the main content,

removing fillers like “um” or “you know” that may not add value to the analysis.

76
Example

A researcher conducting interviews on patients’ experiences with chronic illness would

transcribe the recordings verbatim, ensuring that emotional tones, pauses, and emphasis in

the dialogue are preserved for subsequent analysis.

2. Thematic Analysis

Thematic analysis is a method used to identify, analyze, and report patterns or

themes within qualitative data. It is a flexible approach that can be used across various

qualitative methodologies and involves coding data to generate key themes that represent

the core ideas expressed by participants.

Purpose and Use

 Howitt and Cramer (2020) define thematic analysis as a foundational tool in

qualitative research, providing a structured way to examine and describe patterns

across the data. This method is particularly useful in uncovering the underlying

themes that capture the essence of participants' experiences.

 Gliner et al. (2017) highlight that thematic analysis is commonly used because it does

not require strict adherence to specific theoretical frameworks, making it accessible to

a wide range of research questions.

Steps in Thematic Analysis

1. Familiarization with Data: Researchers immerse themselves in the data by reading

transcripts multiple times.

2. Generating Initial Codes: Identifying meaningful segments of the data and assigning

labels (codes) to them.

3. Searching for Themes: Grouping similar codes into broader categories that represent

major themes.

77
4. Reviewing Themes: Refining and ensuring that the themes accurately represent the

data.

5. Defining and Naming Themes: Clearly defining each theme and how it relates to the

research question.

6. Writing the Report: Presenting the themes in a coherent and logical narrative.

Example

A thematic analysis of interviews with students on their educational experiences might

reveal themes such as "academic pressure," "peer support," and "teacher relationships."

3. Grounded Theory

Grounded theory is a systematic methodology in qualitative research where the

theory is developed inductively from the data. Rather than beginning with a predefined

theory, the researcher constructs the theory during the research process, allowing new

insights to emerge directly from the data.

Purpose and Use

 Howitt (2019) explains that grounded theory is particularly useful for studying social

processes and interactions, as it helps researchers develop a theory that is closely

grounded in empirical data.

 Gliner et al. (2017) emphasize that grounded theory involves continuous comparison

of data and the development of categories that evolve into a theoretical framework,

making it ideal for exploratory research where existing theories are insufficient.

Key Concepts in Grounded Theory

 Coding: The process of breaking down the data into discrete parts and labeling them

with codes.

78
 Constant Comparison: A technique where new data is compared with previously

collected data to refine and develop categories.

 Memo Writing: Researchers write reflective notes (memos) to capture insights about

the developing theory.

Example

A grounded theory study on workplace collaboration could involve analyzing interactions

in teams and developing a theory on how trust and communication evolve in different

work settings.

4. Social Constructionist Discourse Analysis

Social constructionist discourse analysis examines how language is used to

construct social reality. It focuses on how people use language in social contexts to create

meaning, negotiate identities, and establish power dynamics. The analysis explores how

discourses shape and are shaped by social and cultural structures.

Purpose and Use

 Howitt and Cramer (2020) define discourse analysis as a method for studying the

role of language in shaping knowledge, social identities, and power relations. This

approach is particularly valuable in understanding how social issues (e.g., gender,

race, or class) are constructed through everyday talk and media representations.

 Gliner et al. (2017) note that discourse analysis helps researchers explore how

specific ways of talking about topics influence social perceptions and practices.

Key Elements in Discourse Analysis

 Discourses: The different ways people talk about a particular issue (e.g., how mental

illness is framed in the media).

79
 Power Relations: Discourse analysis explores how language reflects and reinforces

social hierarchies.

 Context: Researchers pay close attention to the context in which language is used, as

meaning is shaped by the social and historical background.

Example

A discourse analysis of media portrayals of climate change might reveal competing

discourses, such as the "scientific consensus" versus "climate skepticism," and how these

discourses influence public opinion and policy.

80
4.4 Qualitative data Analysis 2: Conversation Analysis, Foucauldian discourse

analysis, Phenomenology, Interpretative phenomenological analysis, Narrative

Analysis

Qualitative Data Analysis Methods (Part 2)

Qualitative data analysis provides researchers with numerous tools to explore the

complex nature of human experiences, interactions, and social phenomena. Some of the

most widely used methods include Conversation Analysis, Foucauldian Discourse

Analysis, Phenomenology, Interpretative Phenomenological Analysis (IPA), and

Narrative Analysis.

1. Conversation Analysis (CA)

Conversation Analysis (CA) is a method used to examine the structure and pattern of talk

in interactions, focusing on the organization of conversation in everyday settings. It

emphasizes how people use language in social interactions to produce and interpret

meaning.

Purpose and Use

 Howitt (2019) describes CA as a detailed, micro-level analysis of conversational

exchanges. It is especially useful for studying routine, everyday interactions, such as

conversations between doctors and patients or interviews in job settings.

 Gliner et al. (2017) highlight that CA allows researchers to understand not only what

is said but how it is said, including the pauses, interruptions, and timing of

conversation.

Key Features

 Turn-taking: Analyzing how participants in a conversation take turns in speaking.

81
 Adjacency Pairs: Investigating predictable pairs of utterances, such as a question

followed by an answer.

 Repair Mechanisms: How participants handle misunderstandings or mistakes in

conversations.

Example

A CA study of classroom interactions might explore how teachers and students manage

turns in conversation and how interruptions or corrections are handled to maintain

communication flow.

2. Foucauldian Discourse Analysis (FDA)

Foucauldian Discourse Analysis (FDA) is based on the ideas of French philosopher

Michel Foucault. It focuses on how discourses (ways of talking about and understanding

the world) construct knowledge, social identities, and power relationships. FDA is

concerned with how language produces and reproduces power dynamics in society.

Purpose and Use

 Howitt and Cramer (2020) describe FDA as useful for exploring how discourses

shape social practices, institutions, and identities. It differs from traditional discourse

analysis by focusing on the relationship between language, power, and knowledge.

 Gliner et al. (2017) highlight that FDA is often used in critical research to examine

how societal norms and institutional power are constructed through language.

Key Concepts

 Power/Knowledge: Foucault’s concept that power and knowledge are intertwined,

with knowledge being a tool of power.

 Subject Positions: The roles or identities that individuals take on within a particular

discourse.

82
 Discursive Practices: How discourses are enacted through practices in different

social contexts, such as medical, legal, or educational settings.

Example

An FDA study might analyze how discourses around mental health in the media construct

certain identities, such as "the mentally ill" as dangerous or vulnerable, and how these

identities influence public policy and social attitudes.

3. Phenomenology

Phenomenology is a philosophical approach and method aimed at studying

individuals' lived experiences from their own perspective. It seeks to understand the

essence of a phenomenon by exploring how it is experienced and interpreted by people.

Purpose and Use

 Kerlinger (1994) explains phenomenology as a method that focuses on understanding

the subjective, lived experiences of individuals. It emphasizes the importance of

personal perceptions and meanings.

 Howitt (2019) states that phenomenology is particularly useful in psychology,

education, and health sciences to understand deep, personal experiences, such as

trauma, illness, or life transitions.

Key Concepts

 Lived Experience: Central to phenomenology, it refers to how individuals experience

a particular event or situation.

 Essence: The goal of phenomenology is to uncover the core meaning or essence of a

phenomenon, as experienced by multiple individuals.

Example

83
A phenomenological study of grief might involve in-depth interviews with people who

have lost loved ones to explore how they describe and make sense of their emotional

journey.

4. Interpretative Phenomenological Analysis (IPA)

Interpretative Phenomenological Analysis (IPA) is a qualitative research approach that

focuses on how individuals make sense of their personal and social worlds. IPA is rooted

in phenomenology but incorporates elements of hermeneutics (the theory of

interpretation) to understand how individuals interpret their own experiences.

Purpose and Use

 Howitt and Cramer (2020) describe IPA as useful for exploring complex

psychological processes, particularly how individuals make meaning of significant

life events.

 Gliner et al. (2017) emphasize that IPA requires researchers to engage in a double

hermeneutic process, where the researcher interprets the participant’s interpretation of

their own experience.

Steps in IPA

1. Reading and Re-reading: Immersing oneself in the data by reading transcripts

multiple times.

2. Initial Noting: Making detailed notes on the data to capture initial thoughts.

3. Developing Emergent Themes: Identifying themes that represent the participant’s

experiences.

4. Looking for Connections Across Themes: Grouping themes to identify overarching

patterns.

5. Writing the Report: Presenting the themes with illustrative quotes and interpretation.

84
Example

An IPA study might explore how cancer survivors make sense of their illness and

recovery, focusing on how they interpret their emotional, psychological, and social

experiences during and after treatment.

5. Narrative Analysis

Narrative Analysis is a method that focuses on the stories people tell and how these

stories help them make sense of their experiences. It explores the structure, content, and

function of personal narratives to understand how individuals construct meaning and

identity.

Purpose and Use

 Howitt (2019) describes narrative analysis as focusing on the meaning of stories and

how they reflect individuals' personal and social worlds. It is particularly useful in

psychology, sociology, and anthropology to study personal identities and life events.

 Gliner et al. (2017) highlight that narrative analysis allows researchers to explore

how people use stories to give coherence to their lives, make sense of past

experiences, and communicate them to others.

Key Elements in Narrative Analysis

 Plot: The structure of the story, including the events, settings, and characters.

 Causality: How the narrator connects different events and experiences in their life.

 Function: The purpose or meaning behind telling the story, such as making sense of

trauma or asserting an identity.

Example

85
A narrative analysis might explore how veterans tell stories about their military service,

focusing on how they frame their experiences of war and how these narratives influence

their post-service identities.

86
4.5 Evaluating and writing up Qualitative research.

Qualitative research is evaluated and written up differently compared to quantitative

research, focusing on depth, context, and the meaning derived from data rather than

numerical results. Evaluating and writing qualitative research involves addressing

methodological rigor, transparency, and the communication of complex, nuanced data.

Here's how qualitative research can be evaluated and written up, using references from

Evaluating Qualitative Research

1. Credibility

Credibility in qualitative research refers to the trustworthiness of the findings. It is

analogous to internal validity in quantitative research and emphasizes how well the

research reflects the participants' realities.

 Member Checking: As described by Gliner et al. (2017), member checking involves

sharing the findings with participants to confirm the accuracy of the interpretation.

 Triangulation: Using multiple sources of data, methods, or theories to cross-check

and verify the consistency of the findings is a critical strategy for increasing

credibility (Howitt, 2019).

2. Transferability

Transferability refers to how well the findings can be applied to other contexts or settings.

This is equivalent to external validity in quantitative research.

 Thick Description: Howitt & Cramer (2020) highlight the importance of providing

rich, detailed descriptions of the research context and participants to allow readers to

assess the relevance of findings to other settings.

87
 Sampling Considerations: Unlike in quantitative research, qualitative sampling

focuses on depth rather than breadth. Kerlinger (1994) stresses purposeful sampling

over random sampling

88