RESEARCH DESIGN
FATHIMA FIDHA
MEANING
• It is a logical and systematic plan prepared for directing a research
study.
• It specifies the objectives, methodology and techniques to be adopted
for the achievement of the objectives.
• It constitutes the blueprint for the collection, measurement and
analysis of the data.
• Guides investigator in the process of collecting, analyzing and
interpreting observations.
• It provides a systematic plan for the researcher to follow.
2
Research design can be split into various parts:
a) Sampling design which deals with the method of selecting items to be
observed for the given study.
b) Observational design which relates to the conditions under which the
observations are to be made.
c) Statistical design which concerns the question of how many items are
to be observed and how the information and data gathered is to be
analysed.
d) Operational design which deals with the techniques by which the
procedures specified in the sampling, statistical and observational
designs can be carried out.
3
NEED FOR A RESEARCH DESIGN
• Research design is essential for smooth and efficient research operations.
• It saves time, effort, and money, just like a blueprint helps in constructing a house.
• A good design ensures reliable data collection and analysis methods.
• It helps in clear planning and avoids confusion in the research process.
• Poor or no research design can lead to misleading conclusions.
• A well-thought-out design makes it easier to:
•Choose appropriate techniques
•Organize the research steps
•Evaluate results accurately
• Without a proper design, research lacks direction and credibility.
4
Features of A good design
• Flexible: A good design should adapt to changes during the research process.
• Appropriate: The design should fit the purpose and nature of the research problem
• Efficient : A well-structured design uses minimum resources (time, effort, manpower)
to achieve maximum results.
• Economical: A good design should minimize cost while maximizing the value
of the research.
• Minimizes Bias: The design should reduce the influence of personal or external biases.
• Maximizes Reliability: It should ensure that the data collected is dependable and
consistent over time and across researchers.
• Yields Maximum Information: A good design allows for comprehensive data
collection and analysis.
• Allows Multiple Perspective: It provides opportunities to look at the problem from
different angles.
5
Factors to consider
1. Means of obtaining information
2. Availability and skill of the researcher and staff
3. Objective of the study
4. Nature of the problem
5. Time and money available
6
Important Concepts
• Independent Variable A variable that causes or influences change in another
variable.
• Dependent Variable A variable that is affected or measured as a result of
changes in the independent variable
• Example: if height depends upon age, then age is an independent variable
and height is a dependent variable.
• Extraneous Variable: An extraneous variable is any factor other than the
one you’re studying that can affect your results. It’s not the main focus of
your research, but it can still influence the outcome, which can make your
findings less accurate.
7
• Control means minimizing or eliminating the effect of extraneous variables. It
ensures that only the intended independent variable influences the dependent
variable. Especially important in experimental studies.
• Confounded Relationship: A confounded relationship happens when the effect
on the dependent variable is not solely due to the independent variable, but also
influenced by some extraneous variable.
• Research Hypothesis: When a prediction or hypothesised relationship is to be
tested by scientific methods, it is termed as research hypothesis.
• It is a predictive statement that relates an independent variable to a dependent
variable.
• Predictive statements that can’t be tested or verified are not
considered hypotheses.
8
• Experimental hypothesis-testing research- research in which the independent
variable is manipulated
• Non-experimental hypothesis- research in which an independent variable is not
manipulated.
• Control Group : In an experimental hypothesis testing when a group is exposed to
usual conditions, it is termed as control group.
• Experimental Group: when group is exposed to some novel or special conditions,
it is termed as experimental group.
• Treatment: The different conditions under which experimental and control groups
are put are usually referred to as treatments.
• Experiment: The process of examining the truth of a statistical hypothesis, relating
to some research problem is known as an experiment.
• Experimental Unit: It refers to the smallest unit of material or intervention in an
experiment.
9
Types of research design
1. EXPLORATORY RESEARCH DESIGN:
• Also, known as formulative research studies.
• This study is used when the problem is not clearly defined or clearly
understood.
• It is used to gain insights, understand underlying motivations or
behaviours, and develop hypotheses for further, more
conclusive research.
• It transforms vague problems into precise ones for further study.
• Flexible- it does not follow a rigid, structured procedure like descriptive
or experimental research. Instead, the researcher can adapt methods,
questions, and approaches based on what is learned during the study.
10
• Three major methods are used for such studies.
1. Survey of concerning literature-
• Reviewing previous research, theories, and studies related to the problem.
• Helps in formulating the problem precisely and developing hypotheses.
• Researchers should review and build upon existing knowledge.
• If hypothesis have not yet been formulated, his task is to review the available material and
derive hypothesis from it.
• Even if hypotheses are already stated by earlier researchers, they can be:
Modified
Restated
Used as a basis for further research.
• Bibliographical surveys are fruitful for understanding what has already been done and
where gaps exist.
11
2. Experience survey- Means surveying people who have practical experience with the problem
to be studied.
• Objective: to obtain insight into relationships between variables and new ideas relating to the
research problem.
• Respondents must be competent and able to contribute new ideas.
• Should be carefully selected to represent different types of experience.
• Respondents may be interviewed by the investigator.
• Prepare an interview schedule for systematic questioning.
• Ensure flexibility to allow respondents to raise issues/questions not previously considered.
• Likely to be long, possibly lasting hours.
• Often desirable to send a copy of questions beforehand to aid respondent preparation and
advance thinking.
• Helps define the problem more concisely and in formulating research hypotheses.
12
3. Analysis of insight stimulating examples: A fruitful method for suggesting hypotheses,
especially where there is little experience to serve as a guide.
• Consists Intensive study of selected instances of the phenomenon.
• Examination of existing records if available.
• May involve unstructured interviewing or other approaches.
• Effectiveness depends on Attitude of the investigator, Intensity of the study, Researcher’s ability to
draw diverse information into a unified interpretation.
Examples include:
a) Reactions of strangers.
b) Reactions of marginal individuals.
c) Individuals transitioning from one stage to another.
d) Individuals from different social strata.
• Cases providing sharp contrasts or striking features are particularly useful for
hypothesis formulation.
13
2. Descriptive and Diagnostic Research Studies
• Descriptive research studies - Concerned with describing characteristics of an individual or a
group.
• Providing narration of facts and characteristics concerning a group or situation.
• Focuses on -what exists, how it exists, and in what form.
• Example: Studying the demographic characteristics of students in a college.
• Diagnostic research studies -Concerned with determining the frequency with which
something occurs.
• Determining its association with something else.
• Focuses on- why something happens and what factors are associated with it.
• Making specific predictions based on these associations.
• Example: Studying the factors associated with student absenteeism in college and predicting
future absenteeism trends.
14
• Both have common requirements: Must define clearly what is to be measured.
• Need adequate methods for measuring it.
• Must have a clear definition of the population to be studied.
• Aims to obtain complete and accurate information.
• Procedures must be carefully planned.
• Must ensure protection against bias.
• Maximise reliability and economical completion of the research study.
• The design should be rigid.
STEPS INVOLVED:
a. Formulating objectives-It involves defining clearly what the study is about and why it is being
made.
• Ensures that objectives are specific and precise so that the data collected is relevant to the
problem under study.
15
• The researcher knows exactly what information is needed.
• If objectives are not carefully specified, the data collected may not provide the
desired information.
b. Designing the methods of data collection-This involves choosing techniques or methods for
gathering data.
• Should select appropriate methods based on the nature of data needed and objectives of the
study.
• Devise methods carefully to ensure data is reliable, accurate, and unbiased.
• Methods- questionnaires, interviews, observation, examination of records
• Each method has its merits and limitations, so selection should consider the purpose of the
study, availability of resources
• Data collection instruments should be tested and validated before use to ensure clarity.
• Questions must be well examined and unambiguous.
16
• Interviewers should not express their own opinions to avoid bias.
• Observers must be trained to record behaviour accurately and objectively.
c. Selecting the sample: This involves selecting a sample from the population.
• The researcher must determine the sample size- how many observations or respondents are
required.
• Studies are conducted to draw conclusions about populations based on sample analysis
• It is usually not feasible to study the entire population, especially in social research.
• Selecting the right sample so that results are accurate and reliable.
• The sample should yield accurate information with minimum sampling error.
• Be representative of the population, meaning it should reflect the characteristics of
the entire group.
17
d. Collecting the data- Determine where data can be found and time period
of data collection
• Supervision during data collection is necessary to ensure that field staff is collecting
and recording data honestly and without prejudice.
• Checks ensure completeness, comprehensibility, consistency, and reliability.
e. Processing and analysing the data- coding interview replies, observations,
tabulating the data ,performing statistical computations
• If the researcher plans these procedures in detail before starting, it is economical
• For example, if tables are prepared without planning, some may later be useless or
incomplete, requiring rework.
• Coding Should be done carefully to avoid errors, reliability of coders must be
checked.
• Tabulation- accuracy is checked by re-doing a sample of tables.
18
• Statistical Computations: Includes calculating averages, percentages, coefficients.
Probability and sampling analysis may also be used.
• Appropriate tests of significance are conducted to ensure conclusions are correct.
f. Reporting the findings- This is the final task in a research study.
• It involves communicating the findings to others clearly and effectively.
• Prepare the report efficiently and systematically.
• Ensure the layout of the report is well planned, so that all aspects of the research are
included.
19
20
thank you
