Conceptual Understanding
Separate sampling variation, estimation targets and the claims an interval or test can support.

AX26-STAT-201 · 2026-27
Choose an inferential method, justify its assumptions, and explain what a numerical result does and does not establish.
Construct point estimators, interval procedures and tests from a stated sampling model, and report them without converting a p-value into a posterior probability.
01 Sampling and estimation 25h
Learning result Name the sample, the estimand, and the estimator as distinct objects.
Formative check Four-option check
02 Sample mean and standard error 25h
Learning result Derive the standard error of a sample mean under i.i.d. finite-variance sampling.
Formative check Written derivation
03 Likelihood 25h
Learning result Write a likelihood for an i.i.d. sample and distinguish it from a posterior.
Formative check Written derivation
04 Coverage and confidence intervals 35h
Learning result State a coverage claim as a property of the procedure, not of one realised interval.
Formative check Four-option check
05 Hypothesis testing 30h
Learning result Specify H₀, H₁, the test statistic, and the rejection region before looking at the sample.
Formative check Written derivation
06 Errors and power 30h
Learning result Distinguish Type I error, Type II error, and power, and give a case where a small p-value is not a large effect.
Formative check Counterexample
07 Examination synthesis 30h
Learning result Choose estimation, interval, or test for a short applied stem and justify the choice from the sampling model.
Formative check Written derivation
For a named sampling model, derive or select an estimator, an interval with a coverage claim, and a test with explicit hypotheses, then state a limitation of each.
Sampling models, likelihood, standard errors, coverage, Type I/II errors, power.
Write the claim a procedure actually warrants; refuse language that treats one sample as a population proof.
Separate sampling variation, estimation targets and the claims an interval or test can support.
Compute and interpret estimates, intervals and tests under stated assumptions.
Derive sampling distributions or test statistics and transfer the argument to a new design.