Week 1 — Probability, Sampling, and the Logic of Inference

Rebuild probability and frequentist inference from the ground up, using simulation as the microscope, so OLS in Week 2 rests on solid foundations. See ../../TOC.md for the full plan.

Chapters

  1. Ch 1.1 — Joint, Conditional, and the Two Laws That Run Everything (LIE, LTV)
  2. Ch 1.2 — Expectations, Variance, Covariance as Geometry
  3. Ch 1.3 — Estimators and Their Sampling Distributions
  4. Ch 1.4 — The LLN and the CLT, Shown Not Asserted
  5. Ch 1.5 — Hypothesis Testing Done Right

Notebooks (../../../notebooks/week-01/)

  • nb1.1 LIE/LTV by simulation · nb1.2 Covariance matrices & correlation heatmaps · nb1.3 Sampling-distribution explorer · nb1.4 LLN/CLT convergence · nb1.5 Power curves & the t-test from scratch
  • All verified to run headless (matplotlib Agg backend, seeded default_rng(42)).

Problem sets (solutions in Appendix E)

  • PS 1.1 Conditional probability & LIE/LTV · PS 1.2 Expectation/variance/covariance geometry · PS 1.3 Bias/variance/MSE · PS 1.4 CLT/LLN simulation · PS 1.5 Power, size, CIs

Lab, mentor, assessment