Research Methods in Education (M.Ed.

CBCS –
TC – III, 2024) Notes

1 Question 1: Purposes and Areas of Educational Research [7+7]

1.1 Purposes of Conducting Educational Research
Educational research systematically investigates educational phenomena to en-
hance teaching, learning, and institutional practices. Key purposes include:
1. Improving Educational Practices: Identifies effective teaching strategies,
curriculum designs, and assessments.
2. Informing Policy Decisions: Provides evidence for equitable policies.
3. Understanding Learning Processes: Explores cognitive, social, and emo-
tional aspects of learning.
4. Addressing Challenges: Investigates dropout rates, inclusivity, and tech-
nology integration.
5. Theory Development: Builds and tests educational theories.
6. Professional Development: Equips educators with evidence-based prac-
tices.
7. Evaluating Programs: Assesses intervention impacts for resource efficiency.

1.2 Areas Important for School Education

1. Curriculum Development: Ensures relevance and inclusivity (e.g., STEM
reforms).
2. Teaching Methodologies: Studies pedagogies like project-based learning.
3. Assessment and Evaluation: Enhances fairness in measuring progress.
4. Educational Technology: Investigates AI-based platforms for personaliza-
tion.
5. Inclusive Education: Promotes equity for special needs students.
6. Teacher Training: Improves teacher competency.
7. School Management: Enhances leadership and resource allocation.

1
1.3 Alternative: Basic vs. Applied Research [7+7]
1.3.1 Differences
1. Purpose: Basic research expands theoretical knowledge (e.g., memory stud-
ies); applied solves practical problems (e.g., teaching methods).
2. Scope: Basic is broad; applied is context-specific.
3. Outcome: Basic generates theories; applied produces solutions.
4. Time Frame: Basic is long-term; applied is short-term.
5. Examples: Basic—motivation’s effect on learning; applied—reading pro-
grams.
6. Funding: Basic—academic grants; applied—schools/governments.
7. Focus: Basic—curiosity-driven; applied—problem-driven.

1.3.2 Threats in Educational Research

• Basic Research Threats: History (e.g., school events), maturation (e.g., ag-
ing in longitudinal studies), instrumentation (e.g., inconsistent tests), se-
lection bias (e.g., non-random groups), testing effect (e.g., familiarity with
tests).
• Applied Research Threats: Hawthorne effect (e.g., observation bias), ex-
perimenter bias (e.g., researcher enthusiasm), non-representative sampling
(e.g., urban-only samples), diffusion of treatment (e.g., peer sharing), mor-
tality (e.g., dropouts).

2 Question 2: Threats to Validity [7+7]

2.1 Threats to Internal Validity
1. History: External events (e.g., school event). Reduction: Use control groups,
controlled settings.
2. Maturation: Natural changes (e.g., aging). Reduction: Shorten duration,
use control group.
3. Testing: Familiarity from repeated tests. Reduction: Alternate test forms,
increase time gaps.
4. Instrumentation: Inconsistent tools (e.g., grading). Reduction: Standard-
ize tools, train evaluators.
5. Selection Bias: Non-random assignment. Reduction: Random assignment.

2.2 Threats to External Validity

1. Sample Characteristics: Non-representative sample (e.g., urban students).
Reduction: Diverse, random sampling.

2
 2. Setting Specificity: Context-specific results (e.g., rural schools). Reduction:
Varied settings.
3. Pretest Sensitization: Pretests influence behavior. Reduction: Posttest-
only designs.
4. Experimenter Effect: Researcher bias. Reduction: Blind procedures.
5. Hawthorne Effect: Observation alters behavior. Reduction: Minimize study
awareness.

2.3 Alternative: Experimental Research and True Designs [6+8]

2.3.1 Experimental Research
Experimental research manipulates variables to establish cause-and-effect in ed-
ucation. Characteristics: control, randomization, manipulation. Purpose: test
hypotheses (e.g., flipped classroom’s effect on math scores). Steps: hypothesize,
design, collect, analyze. Advantages: high internal validity. Limitations: artifi-
cial settings, ethical constraints.

2.3.2 True Experimental Designs

1. Pretest-Posttest Control Group: Pretest, treat experimental group, posttest
both (e.g., phonics program vs. traditional reading).
2. Posttest-Only Control Group: Treat experimental group, posttest both (e.g.,
inclusive teaching workshop).
3. Solomon Four-Group: Four groups, two pretested, all posttested (e.g., STEM
curriculum impact).
4. Factorial Design: Multiple variables (e.g., teaching method and class size
on history scores).

3 Question 3: Sampling Types and Random Sampling [7+7]

3.1 Types of Sampling
1. Simple Random: Equal chance (e.g., lottery).
2. Stratified: Random from strata (e.g., by gender).
3. Cluster: Random groups (e.g., schools).
4. Systematic: Every nth individual (e.g., 5th student).
5. Purposive: Specific criteria (e.g., experienced teachers).
6. Convenience: Accessible participants (e.g., nearby schools).
7. Snowball: Participant recruitment (e.g., dropouts).

3
3.2 Advantages and Limitations of Random Sampling
• Advantages: Unbiased, generalizable, supports statistics, simple.
• Limitations: Needs population list, time-consuming, non-response bias,
misses subgroups.

3.3 Alternative: Systematic vs. Cluster Sampling [7+7]

3.3.1 Differences
1. Definition: Systematic—every nth individual; cluster—random groups.
2. Unit: Systematic—individuals; cluster—groups.
3. Randomization: Systematic—fixed interval; cluster—random clusters.
4. Application: Systematic—needs list; cluster—impractical lists.
5. Sample Spread: Systematic—even; cluster—clustered.
6. Complexity: Systematic—simpler; cluster—complex.

3.3.2 Advantages and Disadvantages of Systematic Sampling

• Advantages: Simple, evenly distributed, time-efficient, cost-effective.
• Limitations: Needs list, periodicity bias, less random, non-response issues.

4 Question 4: Standard Deviation Calculations [4+5+5]

Given scores: 52, 50, 56, 68, 65, 62, 57, 70 (n = 8).

4.1 (a) S.D. with Assumed Mean at Zero

Sum: 480, Mean: 60, Sum of squared deviations: 29,182. Variance: 29,182
− 602 =
√ 8
47.75. S.D.: 47.75 ≈ 6.91.

4.2 (b) Add 6 to Each Score

New scores: 58, 56, 62, 74, 71, 68, 63, 76. S.D. unchanged: ≈ 6.91.

4.3 (c) Multiply Each Score by 5

New scores: 260, 250, 280, 340, 325, 310, 285, 350. S.D.: 6.91 × 5 ≈ 34.55.

4.4 Alternative: Analysis and Interpretation [6+8]

4.4.1 Analysis and Interpretation
Analysis organizes and summarizes data (e.g., calculating means). Interpreta-
tion explains findings’ meaning (e.g., why scores differ). Analysis is objective;
interpretation is subjective. Both ensure valid, meaningful results.

4
4.4.2 Aspects Before Quantitative Analysis
1. Data cleaning (e.g., remove errors).
2. Data coding (e.g., 1 = male).
3. Normality check (e.g., histograms).
4. Reliability and validity.
5. Sample size (e.g., 30 for t-tests).
6. Variable definition.
7. Missing data handling.
8. Assumption testing (e.g., variance homogeneity).

5 Question 5: Hypotheses and Tools [7+7]

5.1 (a) Hypotheses
A testable statement predicting variable relationships. Types: null (H0 , no ef-
fect), alternative (H1 , effect), directional, non-directional. Characteristics: clear,
testable. Role: guides design and analysis. Example: H0 : Tablets do not improve
scores; H1 : Tablets improve scores.

5.2 (b) Tools and Techniques

Tools: questionnaires, tests, observation checklists, interviews, rating scales. Tech-
niques: observation, case study, content analysis, experimental method, statis-
tical analysis. Selection: reliable, valid, aligned with objectives.

5.3 Alternative: Research Proposal [14]

5.3.1 Title
Impact of AI-Based Personalized Learning on Student Academic Performance.

5.3.2 Introduction
AI enables personalized learning, but its impact on secondary school perfor-
mance is underexplored. This study compares AI-based learning’s effect on math/science
scores.

5.3.3 Objectives
• Compare scores between AI and traditional methods.
• Explore student/teacher perceptions.

5
5.3.4 Research Questions
• Does AI improve math/science scores?
• What are perceptions of AI platforms?

5.3.5 Hypothesis
H0 : No score difference. H1 : AI improves scores.

5.3.6 Methodology
True experimental design. Sample: 100 students (50 AI, 50 traditional). Tools:
tests, questionnaires. Procedure: 12-week intervention, pre/posttests, surveys.
Analysis: t-tests, thematic analysis.

5.3.7 Expected Outcomes

AI improves scores; positive perceptions reported.

5.3.8 Significance
Informs AI adoption, teacher training, and policy.