Research Methods versus Methodology
Research methods refers to all those methods/techniques that are used for conduction of
research. Research methods can be put into the following three groups:
• In the first group we include those methods which are concerned with the collection of
data. These methods will be used where the data already available are not sufficient to
arrive at the required solution;
• The second group consists of those statistical techniques which are used for establishing
relationships between the data and the unknowns;
• The third group consists of those methods which are used to evaluate the accuracy of
the results obtained.
•
Research methodology is a way to systematically solve the research problem. It is the science
of studying how research is done scientifically. In it we study the various steps that are
generally adopted by a researcher in studying his research problem along with the logic behind
them. it is necessary for the researcher to design his methodology for his problem as the same
may differ from problem to problem.
Thus, when we talk of research methodology we not only talk of the research methods but also
consider the logic behind the methods we use in the context of our research study and explain
why we are using a particular method or technique and why we are not using others so that
research results are capable of being evaluated either by the researcher himself or by others.
Research process consists of series of actions or steps necessary to effectively carry out
research and the desired sequencing of these steps.
One should remember that the various steps involved in a research process are not mutually
exclusive; nor they are separate and distinct. They do not necessarily follow each other in any
specific order and the researcher has to be constantly anticipating at each step in the research
process the requirements of the subsequent steps. However, the following order concerning
various steps provides a useful procedural guideline regarding the research process:(1)
formulating the research problem; (2) extensive literature survey; (3) developing the
hypothesis; (4) preparing the research design; (5) determining sample design; (6) collecting the
data; (7) execution of the project; (8) analysis of data; (9) hypothesis testing; (10)
generalisations and interpretation, and (11) preparation of the report or presentation of the
results, i.e., formal write-up of conclusions reached.
1. Formulating the research problem:
1. Types of Research Problems
o Problems related to states of nature (facts, situations).
o Problems related to relationships between variables (cause-effect,
correlations).
2. First Step in Research
o Choose the general area of interest.
o State the problem broadly at first, then narrow it down by resolving
ambiguities.
o Check the feasibility of studying it.
3. Steps in Formulation
o Understand the problem thoroughly.
o Rephrase into analytical/operational terms (specific, precise, measurable).
4. How to Understand the Problem
o Discuss with colleagues/experts.
o Take help from a guide/supervisor (academics) or administrative agencies
(business/government).
5. Role of Literature Review
o Study conceptual literature (theories, concepts).
o Study empirical literature (previous similar studies).
o Helps identify what data/materials are available.
6. Importance of Precise Formulation
o Problem must be stated unambiguously to separate relevant from irrelevant
data.
o Must check objectivity and validity of background facts.
o Clear problem statement decides:
▪ What data to collect
▪ Which relationships to study
▪ What techniques to use
▪ How the final report will look
7. Sequential Refinement
o Formulation happens in stages:
▪ Start broad → refine → make it more specific → more analytical →
realistic given available data/resources.
Formulating a research problem means moving from a broad idea to a precise, specific, and
researchable question, guided by discussion, literature review, and feasibility checks.
2. Extensive Literature Survey
1. After Problem Formulation
oWrite a brief summary/synopsis of the research problem.
oFor Ph.D. work, this synopsis must be submitted for approval.
2. Purpose of Literature Survey
o To study existing knowledge and research related to the problem.
o To identify gaps, methods, and data sources.
3. Sources to Consult
o Abstracting and indexing journals
o Bibliographies (published/unpublished)
o Academic journals, conference proceedings, government reports, books
o Libraries are highly valuable resources.
4. Approach
o One source often leads to another (snowball effect).
o Special attention must be given to earlier similar studies.
An extensive literature survey is done after problem formulation to collect and review all
relevant published and unpublished material, helping the researcher refine and strengthen
their study.
3. Development of Working Hypotheses
1. Definition
o A working hypothesis is a tentative assumption made to be tested logically
or empirically.
o It acts as the focal point of research.
2. Importance
o Guides the researcher and keeps the study on track.
o Sharpens thinking and narrows focus to important aspects.
o Determines the type of data required and the methods of analysis.
o Must be specific and limited to the study at hand.
3. How to Develop Working Hypotheses
o (a) Discussions with colleagues/experts about the problem, its origin, and
objectives.
o (b) Examination of available data/records for patterns or trends.
o (c) Review of earlier studies on similar problems.
o (d) Exploratory personal investigation (e.g., interviews, fieldwork) for deeper
insights.
4. Sources of Hypotheses
o A-priori thinking, examination of data, related studies, expert advice.
o Should be precise, clear, and well-defined.
5. Exception
o In some exploratory or formulative research, hypotheses may not be
needed, since the aim is exploration, not testing.
o But generally, formulating hypotheses is a basic step in most research.
Working hypotheses are tentative, testable assumptions developed from literature, data,
expert input, and exploration. They guide the research process by focusing objectives, data
collection, and analysis.
4. Preparing the Research Design
1. Meaning
o A research design is the conceptual structure within which research is
conducted.
o It ensures collection of relevant evidence with minimum effort, time, and
cost.
2. Purpose of Research Design
o To make research efficient and systematic.
o The type of design depends on the research purpose.
3. Research Purposes
o Exploration → flexible design, allows looking at many aspects.
o Description → design must minimise bias, maximise reliability.
o Diagnosis → focus on identifying causes of a problem.
o Experimentation → design for testing hypotheses under controlled
conditions.
4. Types of Research Designs
o Experimental
▪ Informal: before-and-after without control, after-only with control,
before-and-after with control.
▪ Formal: completely randomized, randomized block, Latin square,
factorial designs (simple/complex).
1. Before-and-after without control
• The researcher measures a variable before applying a treatment (intervention) and
then again after the treatment.
• No control group is used for comparison.
• Example: Measuring students’ test scores before and after a new teaching method in
one class.
• Limitation: Any change could be due to outside factors (not just the treatment).
2. After-only with control
• Two groups are used: one experimental group (receives the treatment) and one
control group (does not).
• Measurements are taken only after the treatment is applied.
• Example: Giving one group a new drug and another group a placebo, then comparing
recovery rates.
• Limitation: Since no “before” measurement exists, we can’t be sure both groups
started at the same level.
3. Before-and-after with control
• Combines the strengths of the above two.
• Both experimental and control groups are measured before and after the treatment.
• Example: Testing two groups of students on math skills before, teaching one group
with a new method (experimental), leaving the other with the old method (control),
then testing both again.
• Advantage: Provides better evidence of treatment effect since initial differences can
be adjusted for.
In short:
• Before-and-after without control → One group, measured before & after.
• After-only with control → Two groups, measured only after.
• Before-and-after with control → Two groups, measured before & after (most reliable
among the three).
1. Completely Randomized Design (CRD)
• Meaning: Subjects (or samples) are assigned to treatments randomly without any
restrictions.
• Use case: Works well when experimental units (subjects) are homogeneous.
• Example: If you want to test 3 fertilizers on crops, you randomly assign each
fertilizer to different plots of land.
2. Randomized Block Design (RBD)
• Meaning: Experimental units are first grouped into blocks (based on similarities), and
then treatments are randomly assigned within each block.
• Why: Reduces the effect of variability among subjects.
• Example: If fields have different soil qualities, each soil type is a block. Fertilizers
are tested within each block so soil effect is minimized.
3. Latin Square Design (LSD)
• Meaning: Treatments are arranged in a square so that each treatment appears only
once in each row and column.
• Why: Controls two sources of variation at the same time (e.g., rows and columns).
• Example: Testing 4 teaching methods across 4 teachers (rows) and 4 classes
(columns), ensuring each method is used once per row & column.
4. Factorial Designs
• Meaning: Studies the effect of two or more factors simultaneously, instead of just
one.
• Types:
o Simple Factorial → Only two factors, e.g., Fertilizer type (A, B) × Water
level (Low, High).
o Complex Factorial → More than two factors, e.g., Fertilizer type × Water
level × Soil type.
• Why: Helps see not just individual effects but also interaction effects (how one
factor changes the effect of another).
oNon-experimental → observational or descriptive approaches.
5. Factors to Consider in Designing Research
o (i) How information will be obtained.
o (ii) Skills/availability of researcher and staff.
o (iii) Organisation and reasoning behind chosen methods.
o (iv) Time available.
o (v) Cost/finance available.
Research design is the plan or blueprint for conducting research. It depends on the research
purpose (exploration, description, diagnosis, experimentation), the type of design chosen
(experimental or non-experimental), and practical constraints like time, skills, and funding.
[Link] Sample Design
1.) Universe vs. Sample
o Universe/Population: all items under study.
o Census: complete enumeration of all items (high accuracy in theory, but
costly, time-consuming, and may still have bias).
o Sample: a subset of the population, studied to save time, money, and effort.
2.) Sample Design
o A definite plan for selecting items from the population before collecting
data.
o Two main types:
1. Probability sampling → each item has a known chance of selection.
2. Non-probability sampling → probability of selection is unknown.
3.) Types of sampling
1.) Deliberate (Purposive) Sampling
o Researcher deliberately selects specific units of the population.
o Includes:
1. Convenience sampling → easy-to-access units.
2. Judgment sampling → researcher’s judgment on what best represents
the population.
o Useful in qualitative research but may lead to bias.
2.) Simple Random Sampling
o Every item in the population has an equal chance of being chosen.
o Methods: lottery, random number tables.
o Ensures unbiased selection.
3.) Systematic Sampling
o Select every kth element from a list after a random start.
o Example: every 10th house, every 15th name.
o Practical when a sampling frame (list) is available.
4.) Stratified Sampling
o Population divided into homogeneous groups (strata).
o Samples are drawn from each stratum using random sampling.
o Ensures better representation of diverse populations.
5.) Quota Sampling
o Similar to stratified sampling but selection is not random.
o Interviewers fill quotas from each stratum using their judgment.
o Cheaper and quicker, but less reliable than random methods.
6.) Cluster & Area Sampling
o Population is divided into clusters; some clusters are randomly selected.
o In area sampling, geographical areas are used as clusters.
o Easier and cost-efficient, but may require larger sample sizes for accuracy.
7.) Multi-Stage Sampling
o Extension of cluster sampling in stages.
o Example: Select states → districts → towns → families.
o Useful for large-scale national or regional studies.
8.) Sequential Sampling
o Sample size not fixed in advance.
o Decision depends on results as survey progresses.
o Common in quality control and industrial studies.
In real research, more than one sampling method can be combined, which is called mixed
sampling. Generally, random sampling is preferred because it reduces bias and allows
estimation of sampling error. However, purposive sampling is useful when the population is
small and specific characteristics need to be studied in detail.
In some cases, other sampling methods (apart from random) may be more practical due to
factors like convenience and low cost. Ultimately, the choice of sampling design depends on
the nature of the research inquiry and other related considerations.
[Link] the data
Often, existing data are inadequate, so researchers need to collect new, appropriate data. This
can be done through experiments or surveys.
Survey methods include:
1. Observation – Directly observing events; limited and costly, unsuitable for large
samples.
2. Personal interviews – Structured questions asked face-to-face; depends heavily on
interviewer’s skill.
3. Telephone interviews – Quick and useful in industrial surveys but less common
overall.
4. Mail questionnaires – Widely used; requires careful questionnaire design and often a
pilot study.
5. Schedules – Trained enumerators fill schedules based on respondents’ answers;
accuracy depends on enumerators’ efficiency.
The choice of method depends on factors like nature, objectives, scope, resources, time,
and accuracy required. Ultimately, common sense and experience guide effective data
collection.
[Link] of the project
Proper execution ensures that collected data are adequate, reliable, and timely. The process
must be systematic and under statistical control.
Key aspects include:
• Structured questionnaires – Coding questions/answers for machine processing.
• Interview-based surveys – Careful selection and training of interviewers using
instruction manuals; field checks to ensure sincerity and efficiency.
• Realism – Monitoring unanticipated factors to maintain accuracy.
• Non-response handling – Identify non-respondents, take a small sub-sample, and use
experts to encourage participation.
8. Analysis of data
Once data are collected, they must be organized, coded, and tabulated for meaningful
analysis.
Key steps include:
• Classification & coding – Raw data are grouped into purposeful categories and
converted into symbols for counting.
• Editing – Improves data quality before coding.
• Tabulation – Data arranged into tables; often done by computers for speed and
handling large variables.
• Statistical analysis – Use of percentages, coefficients, and statistical tests (e.g., tests
of significance, analysis of variance) to validate hypotheses and determine whether
observed differences/relationships are real or due to chance.
The goal is to draw valid inferences and evaluate whether data support or contradict
hypotheses.
9. Hypothesis-testing
After data analysis, the researcher tests the hypotheses formulated earlier to check if the facts
support or contradict them. For this, statistical tests like Chi-square, t-test, and F-test are
commonly used, depending on the research objective and data type. The process leads to
either accepting or rejecting the hypothesis. If no prior hypothesis was set, generalisations
drawn from the data can serve as new hypotheses for future research.
10. Generalisations and interpretation:
• If a hypothesis is repeatedly tested and supported, it can lead to generalisations or
theory-building.
• The true value of research lies in forming such generalisations.
• If no hypothesis was set earlier, the researcher may use interpretation to explain
findings through existing theories.
• Interpretation often raises new questions, leading to further research.
Repeatedly tested hypotheses lead to generalisations (theories), while interpretation explains
findings and often sparks new research questions.
Preparation of the Report/Thesis:
The final step is writing the research report, which must be clear, precise, and well-structured.
Layout:
1. Preliminary pages – Title, date, acknowledgements, foreword, table of contents, list
of tables, graphs, and charts.
2. Main text –
o Introduction: Objectives, methodology, scope, and limitations.
o Summary of findings: Key results and recommendations in simple language.
o Main report: Detailed discussion in logical sequence.
o Conclusion: Final summing up of results.
3. End matter – Appendices (technical data), bibliography, and index.
Style guidelines:
• Write concisely and objectively in simple language.
• Use charts/illustrations only if they add clarity.
• State calculated confidence limits and constraints faced in the study.