Early section (Q1–19): Focuses on descriptive statistics and basic probability — frequency distributions, measures of central tendency and dispersion, skewness/kurtosis, moments, and classical probability rules (conditional probability, independence, Bayes-type reasoning).
Middle section (Q20–42): Shifts to random variables and distribution theory — joint/conditional distributions, expectation, variance decomposition, standard discrete and continuous distributions (Binomial, Poisson, Geometric, Hypergeometric, Exponential, Normal, Cauchy), and correlation/regression basics.
Applied and inferential section (Q43–67): Covers regression theory, estimation (unbiasedness, consistency, efficiency, MVUE), time series trend fitting, demography (mortality, stable population), index numbers, and multivariate concepts like partial/intra-class correlation.
Later section (Q68–100): Heavily weighted toward inferential statistics and design of experiments — matrices (a recurring but minor thread), interpolation, factorial/RBD/LSD experimental designs, hypothesis testing (MLE properties, unbiased tests, non-parametric tests like Mann-Whitney and runs test), sampling theory (SRS, cluster sampling), and Markov chains as a closing advanced topic.
Key trends noticed:
- Strong emphasis on theoretical properties of estimators (unbiasedness, consistency, efficiency, sufficiency) — appears repeatedly (Q45–47, 82, 86, 95, 96).
- Distribution theory is the single largest thematic cluster, spanning discrete, continuous, and sampling distributions.
- Design of experiments (RBD, LSD, factorial, confounding) gets dedicated but concentrated coverage near the end (Q71–79).
- Matrix algebra appears only marginally (Q68, 97, 98)
- Time series and index numbers form a small but distinct applied cluster (Q51, 58–62, 71–72, 76).
Paper is heavily theory-and-formula driven, testing conceptual depth across the full statistics curriculum with a visible tilt toward distribution theory and estimation/inference in the second half.
Course Purchase Query 