सSaral Shiksha Yojna
Courses/Behavioral Research: Statistical Methods

Behavioral Research: Statistical Methods

CG3.402
Vinoo Alluri•Monsoon 2025-26•4 credits
Sample Papers/100-mark mock paper · Paper 2

100-mark mock paper · Paper 2

Duration: 120 min • Max marks: 100

Section A — MCQs (20 × 1 = 20 marks)

20 marks
  1. 1.Likert-scale responses (Strongly Disagree → Strongly Agree) are best described as: (a) Nominal (b) Ordinal (c) Interval (d) Ratio1 m
  2. 2.The standard error of the mean (SEM) is computed as: (a) σ × √n (b) σ / √n (c) σ² / n (d) σ × n1 m
  3. 3.Which of these is a confound, not a treatment effect? (a) Random assignment differences (b) Differences in pre-treatment groups due to a third variable (c) Sampling variability (d) Measurement noise1 m
  4. 4.A 95% CI for the difference of means is [−0.5, 3.2]. The null value (0) is: (a) Inside the interval, so we fail to reject H₀ at α = .05 (b) Outside the interval, so we reject H₀ (c) The interval is too wide to be useful (d) Cannot be determined1 m
  5. 5.Which of these tests assumes sphericity? (a) Independent t-test (b) Pearson correlation (c) Repeated-measures ANOVA (d) Chi-square1 m
  6. 6.Which is true of the F-distribution? (a) Symmetric around 0 (b) Always greater than or equal to 0, right-skewed (c) Identical to a t-distribution (d) Used for testing categorical data1 m
  7. 7.A correlation coefficient of r = −0.85 indicates: (a) Weak negative relationship (b) Strong positive relationship (c) Strong negative linear relationship (d) No relationship1 m
  8. 8.Cohen's d = 0.5 is conventionally interpreted as: (a) Small (b) Medium (c) Large (d) No effect1 m
  9. 9.Which of the following is true of an unbiased estimator? (a) It always equals the true parameter (b) Its expected value equals the true parameter (c) It has the smallest variance (d) It is always larger than the parameter1 m
  10. 10.A boxplot shows a point at 1.7 × IQR above Q3. Is this flagged as an outlier? (a) Yes — beyond 1.5 × IQR (b) No — must be beyond 3 × IQR (c) Cannot tell without skew (d) No — must be beyond 2 SD1 m
  11. 11.Which of the following best describes a heat map? (a) A 3D bar chart (b) A matrix where colour encodes the value of each cell (c) A type of pie chart (d) A scatterplot with density1 m
  12. 12.Anscombe's quartet teaches us that: (a) Mean and SD are sufficient summaries (b) Different datasets can share summary statistics but differ visually — always plot data (c) Outliers should always be removed (d) Pearson r is the only valid correlation1 m
  13. 13.A factor loading of 0.85 on a single factor indicates: (a) Weak association (b) Strong association between the item and that factor (c) The item is irrelevant (d) Negative correlation with the factor1 m
  14. 14.Parallel analysis is used to: (a) Test linearity in regression (b) Determine the number of factors/components to retain (c) Compute correlations (d) Adjust p-values1 m
  15. 15.Which of the following correctly describes the relationship between α and Type I error? (a) α is the probability of Type II error (b) α is the probability of Type I error if H₀ is true (c) α decreases when sample size increases (d) α is the false discovery rate1 m
  16. 16.A study claims a 5-IQ-point gap between two groups, p < .001, n = 50,000 per group. The most likely interpretation: (a) A practically significant and important effect (b) Likely real but practically small (c) A p-hacking artefact (d) Sampling error1 m
  17. 17.The Welch t-test differs from Student's t-test in that it: (a) Assumes equal variances (b) Does not assume equal variances (c) Uses ranks (d) Is for paired data1 m
  18. 18.A Bayes Factor BF₀₁ = 25 implies: (a) Strong evidence for H₁ (b) Strong evidence for H₀ (c) Inconclusive (d) The null is definitely true1 m
  19. 19.A study measures cortisol levels (μg/dL) before and after a stress task in the same 40 participants. The appropriate test is: (a) Independent t-test (b) Paired t-test (c) Chi-square (d) ANOVA1 m
  20. 20.The intercept β₀ in Y = β₀ + β₁X + ε represents: (a) The slope (b) Predicted Y when X = 0 (c) The mean of X (d) The residual1 m

Section B — MSQs (10 × 2 = 20 marks)

20 marks
  1. 1.Which are true about p-values? (a) p = probability that H₀ is true (b) p depends on the test statistic and sample size (c) p is computed assuming H₀ is true (d) p < .05 means H₁ is true (e) Smaller p ≠ larger effect2 m
  2. 2.Which are properties of the Normal distribution? (a) Symmetric (b) Mean = median = mode (c) Defined by two parameters (μ, σ) (d) Has heavier tails than the t-distribution (e) About 95% of values lie within ±2σ2 m
  3. 3.Which apply to confirmatory factor analysis (CFA)? (a) Theory-driven (b) Number of factors specified in advance (c) Used to discover latent structure with no prior model (d) Tests model fit (e) Allows hypothesis testing about factor structure2 m
  4. 4.Which are valid uses of Chi-square tests? (a) Goodness-of-fit (b) Test of independence in a contingency table (c) Comparing means of two groups (d) Test of two-by-two categorical association (e) Testing correlation between continuous variables2 m
  5. 5.Which can be detected through residual plots in regression? (a) Non-linearity (b) Heteroscedasticity (c) Outliers/leverage (d) Multicollinearity (e) Normality of errors2 m
  6. 6.A researcher uses Tukey's HSD after a significant one-way ANOVA. Why? (a) Tukey controls FWER for all pairwise comparisons (b) Tukey is the only post-hoc test available (c) Tukey adjusts for multiple comparisons (d) Tukey is appropriate after a significant omnibus F (e) Tukey replaces the F-test2 m
  7. 7.Which conditions favor parametric tests over nonparametric? (a) Interval/ratio DV (b) Approximately normal data (c) Large sample sizes (d) Ordinal DV (e) Roughly equal variances across groups2 m
  8. 8.A Bayes Factor analysis is preferred to a p-value when: (a) Evidence for the null is of interest (b) Optional stopping is desired (c) The researcher wants to incorporate prior knowledge (d) They want to fail to reject H₀ definitively (e) Effect size needs to be reported2 m
  9. 9.Which are valid forms of sampling bias? (a) Selection bias (b) Self-selection bias (c) Survivorship bias (d) Random sampling (e) Non-response bias2 m
  10. 10.Which sources can inflate Type I error? (a) Running many tests without correction (b) Optional stopping (c) Post-hoc subgroup analyses (d) Larger sample size (e) Selecting predictors after looking at the data2 m

Section C — Short Descriptive (6 × 5 = 30 marks)

30 marks

    Section D — Long Descriptive (3 × 10 = 30 marks)

    30 marks

      Track your attempt locally — score and time are recorded in your browser. (Coming soon: timed-attempt mode.)