Behavioral Research: Statistical Methods
CG3.402Vinoo Alluri•Monsoon 2025-26•4 credits
PYQ-style paper · Paper C
Duration: 120 min • Max marks: 50
Section 1 — Objective Questions (15 marks)
0 marks- 1.Karthik is observing students in the library. He notices that students who know they are being observed sit more upright and read more attentively. This is: (a) Demand characteristics (b) Reactivity / Hawthorne effect (c) History effect (d) Confounding
- 2.A test always gives the same result when administered to the same person twice. It is: (a) Valid (b) Reliable (c) Both (d) Neither
- 3.The kurtosis of a distribution measures: (a) Skewness (b) Heaviness/peakedness of the tails (c) Mean (d) Median
- 4.A regression model has **adjusted R² < R²**. This is: (a) An error in computation (b) Expected — adjusted R² penalizes for the number of predictors (c) Indicative of perfect fit (d) Sign of multicollinearity
- 5.In a normal distribution, approximately what percentage of values fall within ±1 SD of the mean? (a) 50% (b) 68% (c) 95% (d) 99.7%
- 6.The expected value of a sample mean drawn from a population with mean μ is: (a) 0 (b) μ (c) σ (d) μ/n
- 7.Lakshmi takes a sample of n = 50 from a Beta-distributed (skewed) population. By the CLT, the sampling distribution of her sample mean is: (a) Beta-distributed (b) Right-skewed (c) Approximately normal (d) Uniform
- 8.Two events A and B are independent if: (a) P(A) = P(B) (b) P(A ∩ B) = P(A) × P(B) (c) P(A ∩ B) = 0 (d) P(A | B) = 0
- 9."Demand characteristics" refers to: (a) Statistical assumptions of t-tests (b) Cues in the experimental setting that lead participants to guess the hypothesis and adjust behavior (c) Sampling biases (d) Effect of placebo
- 10.Friedman's test is the nonparametric counterpart of: (a) Independent t-test (b) Paired t-test (c) One-way ANOVA (d) Repeated-measures ANOVA
- 11.Suhasini draws a boxplot of student grades and finds the median sits at the right (upper) end of the box. This suggests: (a) Symmetric distribution (b) Left-skewed distribution (c) Right-skewed distribution (d) Bimodal distribution
- 12.A reliability study at IIIT-H gives the same questionnaire to the same students 3 weeks apart. Which type of reliability is being assessed? (a) Internal consistency (b) Test-retest (c) Inter-rater (d) Parallel forms
- 13.A salesperson shows a graph of cumulative sales over 5 years to claim "consistent growth". Why might this graph be misleading? (a) Cumulative graphs always trend upward, even when month-over-month sales decline; they exaggerate consistency (b) The data are too recent (c) Cumulative graphs cannot be drawn (d) They never include zero
- 14.A line plot of "company revenue" starts the y-axis at 80 lakhs and ends at 120 lakhs, making a 5% rise look dramatic. This is: (a) Truncated y-axis / scale manipulation (b) Correct visualization (c) Histogram error (d) Confidence-interval issue
- 15.Vinay performs a one-tailed t-test (H₁: μ_treatment > μ_control). The two-tailed p was 0.08. The one-tailed p (in the predicted direction) is approximately: (a) 0.16 (b) 0.04 (c) 0.08 (d) Cannot be determined
- 16.Anushka measures "number of friends" — a count variable. The most appropriate visualization for its distribution is: (a) Pie chart (b) Histogram or bar chart (c) Spider plot (d) Line plot
- 17.A psychologist reports "Cohen's d = 0.95, 95% CI [0.7, 1.2]." This means: (a) Small effect (b) Large effect; CI excludes zero, so significant; effect size estimate is fairly precise (c) Non-significant (d) The CI is wrong
- 18.In a Chi-square test of independence on a 4 × 3 contingency table, the degrees of freedom are: (a) 12 (b) 7 (c) 6 (d) 5
- 19.Aditya is comparing **median** reaction times across 4 IIIT-H hostels. Data are heavily skewed. The best test: (a) One-way ANOVA (b) Kruskal-Wallis test (c) Repeated-measures ANOVA (d) Independent t-test
- 20."Posterior ∝ Likelihood × Prior" is the proportional form of: (a) Frequentist inference (b) Bayes' rule (c) The Law of Large Numbers (d) Sphericity
Section 2 — Short Descriptive (15 marks)
0 marksSection 3 — Long Descriptive (20 marks)
0 marksTrack your attempt locally — score and time are recorded in your browser. (Coming soon: timed-attempt mode.)