Learning Resources
Use the reading guide for assignments and the offline Python labs for executable practice. These resources have distinct roles:
- Introduction to Probability, Blitzstein and Hwang: primary probability backbone from the local library; use its contents to locate assigned topics.
- Mathematics for Computer Science: alternate proof-oriented explanations of events, random variables, expectation, and deviation bounds.
- Harvard Stat110 practice and homework: topic practice followed by mixed problems, with solutions available for feedback.
- Introduction to Probability, Statistics, and Random Processes: CLT: another explicit statement of the i.i.d. finite-variance theorem.
- NIST confidence intervals for a proportion: primary reference for the Wilson formula and comparison with Wald and exact-binomial procedures.
No additional book purchase is required. More books are useful when they supply a different explanation or new independent problems; repeated reading of the same derivation does not replace solving and defending an unfamiliar problem.
Resource-use protocol
First attempt a problem and name the obstacle. Consult one targeted source section. Close it and reconstruct the argument. Change an input or assumption and solve again. Record assistance and what you checked independently in the evidence template.
Use reference and selective reading to resolve topic navigation. The instructor guide documents what has been checked and what still needs learner feedback.
Continuous models and inference extension
Use the inference source map for free primary material on joint densities, likelihood, Bayesian parameters and randomization. No additional purchase is required.