UNIT 3: Conceptual framework,

research philosophy, and

design

1
 What are frameworks in research?
• Frameworks are essential to bridge the gaps in research.

• They aid in clearly setting the goals, priorities, and relationship between variables.

• Frameworks in research particularly help in chalking clear process details.

• There are several types of frameworks but the most common ones are two and both
have significant role in research.

• They are Theoretical and conceptual frameworks.

• Other types of frameworks include empirical, descriptive, normative, and explanatory.

2
 Theoretical framework
• This type of framework is an overarching set of concepts, ideas, and assumptions that
help to explain and interpret a phenomenon.

• It provides a theoretical perspective on the phenomenon being studied and helps

researchers to identify the relationships between different concepts.

• Examples of theoretical frameworks are:

 Social learning theory
 Maslow’s hierarchy of needs
 Ecological systems theory
 Feminist theory
 Cognitive behavior theory
 Attachment theory
 Critical race theory 3
 When to have a theoretical framework
• A theoretical framework should be developed when conducting research in any
discipline, as it provides a foundation for understanding the research problem and
guiding the research process.

• A theoretical framework is essential when conducting research on complex phenomena,

as it helps to organize and structure the research questions, hypotheses, and findings.

• A theoretical framework should be developed when the research problem requires a

deeper understanding of the underlying concepts and principles that govern the
phenomenon being studied.

• A theoretical framework should be developed when conducting research that seeks to

address a specific gap in knowledge, as it helps to define the problem and identify
potential solutions. 4
 When to have a theoretical framework cont’d
• A theoretical framework is also important when conducting research that involves the
analysis of existing theories or concepts, as it helps to provide a framework for
comparing and contrasting different theories and concepts.

• A theoretical framework should be developed when conducting research that seeks to

make predictions or develop generalizations about a particular phenomenon, as it helps
to provide a basis for evaluating the accuracy of these predictions or generalizations.

• Finally, a theoretical framework should be developed when conducting research that

seeks to make a contribution to the field, as it helps to situate the research within the
broader context of the discipline and identify its significance.

5
 Purpose of theoretical framework
• Provides a conceptual framework for the study.

• Guides the research design.

• Supports the interpretation of the research findings.

• Enhances the credibility of the research.

• Facilitates communication and collaboration.

6
 What is conceptual framework?
• A conceptual framework is a way of organizing and understanding complex ideas,
theories, or concepts in research.

• A conceptual framework illustrates the expected relationship between your variables.

• A conceptual framework sets forth the standards to define a research question and find
appropriate, meaningful answers for the same.

• It connects the theories, assumptions, beliefs, and concepts behind your research and
presents them in a pictorial, graphical, or narrative format.

• A conceptual framework is part of the theoretical framework in a larger sense, yet there
are variations between them. 7
 What is conceptual framework cont’d?
• A critical facet a conceptual framework unveils is the relationship the researchers have
with their research.

• It closely highlights the factors that play an instrumental role in decision-making,

variable selection, data collection, assessment of results, and formulation of new
theories.

• Consequently, if you, the researcher, are at the forefront of your research battlefield,
your conceptual framework is the most powerful arsenal in your pocket.

8
 Developing a conceptual framework in research
• A conceptual framework is a representation of the relationship you expect to see
between your variables, or the characteristics or properties that you want to study.

• Conceptual frameworks can be written or visual and are generally developed based on
a literature review of existing studies about your topic.

• Step 1: Choose your research question.

Example: Research question

Let’s say you want to study whether students who study more hours get higher exam
scores.
To investigate this question, you can use methods such as an experiment or a survey to
9
test the relationship between variables.
 Developing a conceptual framework in research cont’d
• However, before you start collecting your data, consider constructing a conceptual
framework.

• This will help you map out which variables you will measure and how you expect them to
relate to one another.

• Step 2: Select your independent and dependent variables

 In order to move forward with your research question and test a cause-and-effect
relationship, you must first identify at least two key variables: your independent and
dependent variables.

Dependent variable is the variable that is measured or observed in a research study.

10 It is
 Developing a conceptual framework in research cont’d
• An independent variable is the variable that is manipulated or controlled by the researcher
in a research study. It is the cause or factor that influences the dependent variable.

 Following our previous example:

The expected cause, “hours of study,” is the independent variable (the predictor, or
explanatory variable).
The expected effect, “exam score,” is the dependent variable (the response, or outcome
variable).

• In other words, you suspect that “exam score” depends on “hours of study.”

• Thus, your hypothesis will be that the more hours a student studies, the better they will do
on the exam. 11
 Developing a conceptual framework in research cont’d
 Note that causal relationships often involve several independent variables that affect
the dependent variable.

 For the purpose of this example, we’ll work with just one independent variable (“hours
of study”).

• Step 3: Visualize your cause-and-effect relationship

We demonstrate this using basic design components of boxes and arrows. Here, each
variable appears in a box.

To indicate a causal relationship, each arrow should start from the independent
variable (the cause) and point to the dependent variable (the effect). 12
Developing a conceptual framework in research cont’d

13
 Developing a conceptual framework in research cont’d
• Step 4: Identify other influencing variables

 It’s crucial to identify other variables that can influence the relationship between your
independent and dependent variables early in your research process.

 Some common variables to include are moderating, mediating, and control variables.

Moderating variable (or moderators) alter the effect that an independent variable has
on a dependent variable.

In other words, moderators change the “effect” component of the cause-and-effect
relationship.
14
 Developing a conceptual framework in research cont’d
 Example: Moderator

 We expect that the number of hours a student studies is related to their exam score—
i.e., the more you prepare, the higher your score will be.

 Let’s add the moderator “IQ.” Here, a student’s IQ level can change the effect that the
variable “hours of study” has on the exam score. The higher the IQ, the fewer hours of
study are needed to do well on the exam.

 We expect that the “IQ” moderator moderates the effect that the number of study hours
has on the exam score.

15
Developing a conceptual framework in research cont’d

16
 Developing a conceptual framework in research cont’d
 Now we’ll expand the framework by adding a mediating variable.

 Mediating variables link the independent and dependent variables, allowing the relationship
between them to be better explained.

 Example: Mediator
The mediating variable of “number of practice problems completed” comes between the
independent and dependent variables.

Hours of study impacts the number of practice problems, which in turn impacts the exam
score.

In this case, the mediator helps explain why studying more hours leads to a higher exam
score. The more hours a student studies, the more practice problems they will complete;
17
the
more practice problems completed, the higher the student’s exam score will be.
 Developing a conceptual framework in research cont’d

Keep in mind that mediating variables can be difficult to interpret. Take care when drawing
conclusions from them 18
 Developing a conceptual framework in research cont’d
 It’s important not to confuse moderating and mediating variables.

 A moderating variable is not affected by the independent variable, even though it

affects the dependent variable. For example, no matter how many hours you study (the
independent variable), your IQ will not get higher.

 A mediating variable is affected by the independent variable. In turn, it also affects the
dependent variable. Therefore, it links the two variables and helps explain the
relationship between them.

 Lastly, control variables must also be taken into account. These are variables that are
held constant so that they don’t interfere with the results.
19
 Developing a conceptual framework in research cont’d
Even though you aren’t interested in measuring them for your study, it’s crucial to be
aware of as many of them as you can be.

Example: Control variable

It is very possible that if a student feels ill, they will get a lower score on the exam.
However, we are not interested in measuring health outcomes a part of our research.

This makes “health” a good candidate for a control variable. It still impacts our results,
but we aren’t interested in studying it.

Now, we add “health” to our conceptual framework, but decide to keep it constant. This
means we’ll only include participants who are in good health on the day of the exam.
20
Developing a conceptual framework in research cont’d

21
 Research philosophy and paradigms
• Research philosophy is a term that refers to the set of beliefs, assumptions, and principles that
underlie the way you approach your research project.

• It reflects what kind of knowledge and insight you expect to gain from your study, and how you
collect, analyze, and use data.

• There are different types of research philosophy, such as positivism, interpretivism, and
pragmatism, that have different implications for your research methodology and design.

• Choosing a research philosophy depends on the nature of your research question, the field or
discipline you are studying, and your personal preferences and worldview.

• Research philosophy is an important component of any research project, as it helps you to

clarify your research objectives, scope, and limitations. It also helps you to communicate22your
research findings and contributions to the relevant audience.
 Paradigm 1: Positivism
• When you think positivism, think hard sciences – physics, biology, astronomy, etc.

• Simply put, positivism is rooted in the belief that knowledge can be obtained through
objective observations and measurements.

• In other words, the positivist philosophy assumes that answers can be found by
carefully measuring and analyzing data, particularly numerical data.

• As a research paradigm, positivism typically manifests in methodologies that make use

of quantitative data.

• Studies with a positivist research philosophy typically aim for objectivity, generalizability
and replicability of findings. 23
 Paradigm 1: Positivism cont’d
• Assume you wanted to investigate the relationship between a particular dietary
supplement and weight loss.

• In this case, you could design a randomized controlled trial (RCT) where you assign
participants to either a control group (who do not receive the supplement) or an
intervention group (who do receive the supplement).

• With this design in place, you could measure each participant’s weight before and after
the study and then use various quantitative analysis methods to assess whether
there’s a statistically significant difference in weight loss between the two groups.

• By doing so, you could infer a causal relationship between the dietary supplement and
weight loss, based on objective measurements and rigorous experimental design.
24
 Paradigm 2: Interpretivism
• If you can imagine a spectrum of research paradigms, interpretivism would sit more
or less on the opposite side of the spectrum from positivism.

• Essentially, interpretivism takes the position that reality is socially constructed.

• In other words, that reality is subjective, and is constructed by the observer through
their experience of it, rather than being independent of the observer (which, if you
recall, is what positivism assumes).

• An interpretivistic philosophy also typically manifests in the adoption of a qualitative

methodology, relying on data collection methods such as interviews, observations,
and textual analysis.
25
 Paradigm 2: Interpretivism cont’d
• Assume that you’re interested in understanding the experiences of individuals suffering
from chronic pain.

• In this case, you might conduct in-depth interviews with a group of participants and ask
open-ended questions about their pain, its impact on their lives, coping strategies, and
their overall experience and perceptions of living with pain.

• You would then transcribe those interviews and analyze the transcripts, using thematic
analysis to identify recurring themes and patterns.

• Based on that analysis, you’d be able to better understand the experiences of these
individuals, thereby satisfying your original research aim.
26
 Paradigm 3: Pragmatism
• As the name suggests, pragmatism takes a more practical and flexible approach, focusing on the
usefulness and applicability of research findings, rather than an all-or-nothing, mutually exclusive
philosophical position.

• This allows you, as the researcher, to explore research aims that cross philosophical boundaries,
using different perspectives for different aspects of the study.

• With a pragmatic research paradigm, both quantitative and qualitative methods can play a part,
depending on the research questions and the context of the study.

• This often manifests in studies that adopt a mixed-method approach, utilizing a combination of
different data types and analysis methods.

• Ultimately, the pragmatist adopts a problem-solving mindset, seeking practical ways to achieve
27
diverse research aims.
 Paradigm 3: Pragmatism cont’d
• Imagine that you want to investigate the effectiveness of a new teaching method in
improving student learning outcomes.

• In this case, you might adopt a mixed-methods approach, which makes use of both
quantitative and qualitative data collection and analysis techniques.

• One part of your project could involve comparing standardized test results from an
intervention group (students that received the new teaching method) and a control
group (students that received the traditional teaching method).

• Additionally, you might conduct in-person interviews with a smaller group of students
from both groups, to gather qualitative data on their perceptions and preferences
regarding the respective teaching methods. 28
 Research design
• A research design is a plan or strategy that guides how you conduct your research project.

• It is the blueprint of a scientific study.

• It involves making decisions about the following aspects of your research:

 The overall aim and objectives of your research
 The type of data you need to answer your research question
 The methods you will use to collect and analyze your data
 The ethical and practical issues you need to consider

• A research design helps you to ensure that your research is systematic, rigorous, and valid.

• It also helps you to communicate your research plan and findings to others.
29
 Research design elements
• Research design elements include the following:
 Clear purpose: The research question or hypothesis must be clearly defined and focused.

 Sampling: This includes decisions about sample size, sampling method, and criteria for
inclusion or exclusion. The approach varies for different research design types.

 Data collection: This research design element involves the process of gathering data or
information from the study participants or sources. It includes decisions about what data to
collect, how to collect it, and the tools or instruments that will be used.

 Data analysis: All research design types require analysis and interpretation of the data
collected. This research design element includes decisions about the statistical tests or methods
that will be used to analyze the data, as well as any potential confounding variables or biases
that may need to be addressed.

 Type of research methodology: This includes decisions about the overall approach for
30
the
study.
 Research design elements cont’d
 Time frame: An important research design element is the time frame, which includes decisions
about the duration of the study, the timeline for data collection and analysis, and follow-up
periods.

 Ethical considerations: The research design must include decisions about ethical considerations
such as informed consent, confidentiality, and participant protection.

 Resources: A good research design takes into account decisions about the budget, staffing, and
other resources needed to carry out the study.

• The elements of research design should be carefully planned and executed to ensure
the validity and reliability of the study findings.

31
 Characteristics of a good research design
• Neutrality: Right from the study assumptions to setting up the study, a neutral stance
must be maintained, free of pre-conceived notions. The researcher’s expectations or
beliefs should not color the findings or interpretation of the findings. Accordingly, a good
research design should address potential sources of bias and confounding factors to be
able to yield unbiased and neutral results.

• Reliability: Reliability is one of the characteristics of research design that refers to

consistency in measurement over repeated measures and fewer random errors. A
reliable research design must allow for results to be consistent, with few errors due to
chance.

• Validity: Validity refers to the minimization of nonrandom (systematic) errors. A good

research design must employ measurement tools that ensure validity of the results.
32
 Characteristics of a good research design cont’d
• Generalizability: The outcome of the research design should be applicable to a larger
population and not just a small sample. A generalized method means the study can be
conducted on any part of a population with similar accuracy.

• Flexibility: A research design should allow for changes to be made to the research plan
as needed, based on the data collected and the outcomes of the study.

NB: A well-planned research design is critical for conducting a scientifically rigorous study
that will generate neutral, reliable, valid, and generalizable results.

At the same time, it should allow some level of flexibility.

33
 Different types of research designs
• Broadly, research design types can be divided into qualitative and quantitative
research.

• Qualitative research is subjective and exploratory. It determines relationships between

collected data and observations. It is usually carried out through interviews with open-
ended questions, observations that are described in words, etc.

• Quantitative research is objective and employs statistical approaches. It establishes

the cause-and-effect relationship among variables using different statistical and
computational methods. This type of research is usually done using surveys and
experiments.

34
 Qualitative research vs Quantitative research
Qualitative research design Quantitative research design
Deals with subjective aspects, e.g., experiences, beliefs, Measures different types of variables and describes
perspectives, and concepts. frequencies, averages, correlations, etc.
Deals with non-numerical data, such as words, images, and Tests hypotheses about relationships between variables.
observations. Results are presented numerically and statistically.
In qualitative research design, data are collected via direct Quantitative research design is empirical. Data collection
observations, interviews, focus groups, and naturally methods involved are experiments, surveys, and
occurring data. Methods for conducting qualitative research observations expressed in numbers. The research design
are grounded theory, thematic analysis, and discourse categories under this are descriptive, experimental,
analysis. correlational, diagnostic, and explanatory.

Data analysis involves interpretation and narrative analysis. Data analysis involves statistical analysis and hypothesis
testing.
The reasoning used to synthesize data is inductive. The reasoning used to synthesize data is deductive.
Typically used in fields such as sociology, linguistics, and Typically used in fields such as economics, ecology,
anthropology. statistics, and medicine.
Example: Focus group discussions with women farmers Example: Testing the effectiveness of a new treatment for
about climate change perception. insomnia.

35
 Different types of research designs cont’d
• Descriptive research design is used to describe a phenomenon or situation using surveys,
questionnaires, interviews, and observations. It can provide an accurate and detailed
portrayal of a particular group, event, or situation.

• Correlational research design is used to determine if there is a relationship between two or

more variables using statistical methods. It can identify the strength and direction of the
relationship between the variables.

• Experimental research design is used to investigate cause-and-effect relationships between

variables by manipulating one variable and measuring the effect on another variable. It can
establish causality.

• Quasi-experimental research design is similar to experimental research design, but it lacks

some features of a true experiment, such as random assignment or a control group. 36
It is
used when a true experiment is not feasible or ethical
 Different types of research designs cont’d
• Case study research design is used to investigate a single case or a small number of
cases in depth using various methods, such as interviews, observations, and document
analysis. It can provide an in-depth understanding of a particular case or situation.

• Longitudinal research design is used to study changes in a phenomenon over time by

collecting data at multiple time points and analyzing the changes that occur. It can
provide insights into the development, growth, or decline of a phenomenon over time.

• Cross-sectional research design is a type of research design in which you collect data
from many different individuals at a single point in time. It can be used to measure the
prevalence of an outcome or a characteristic in a population, or to investigate the
association between two or more variables.

37