Skip to content

Lecture notes. Written from the material of Berkeley Stat 210A, licensed CC BY 4.0. These are notes, not a transcript: the material has been reorganised and rewritten. This adaptation carries the same licence, and the original is linked above.

19. Course Overview and Schedule

What this covers

This chapter is not a single lecture's mathematics — it is the map of the term that the course's own home pages lay out. It answers two questions a reader needs answered before opening any lecture in this course: what kind of course Statistics 210A is and who it is for, and in what order the theory is built up across a semester of lectures, recitations, homework, and the final exam. It assumes nothing beyond wanting to know what lies ahead; no probability or statistics content is developed here, since none is given in the source pages — only the schedule of it.

What the course is

Stat 210A is UC Berkeley's introductory Ph.D.-level course in theoretical statistics. The course's own description is blunt about its pace: it is "a fast-paced and demanding course intended to prepare students for research careers in statistics." It is offered every fall — the department's site shows Fall 2024, Fall 2025 and Fall 2026 iterations — with the same overall shape repeating from year to year.

The course is aimed at incoming statistics Ph.D. students. Undergraduates who want to take it are asked to fill out a permission-code request form describing their background, and are pointed to a set of frequently-asked-questions covering preparation and review material; that background review is referred to by the home page but not included in it.

How a term runs

Three platforms carry the logistics: a syllabus page for basic course information, Gradescope for turning in homework, EdStem for announcements and technical discussion — explicitly not the place for homework spoilers — and bCourses for lecture videos and homework solutions.

Within a typical week the rhythm is: one or two lectures, each followed by a posted set of handwritten notes; roughly one new homework set assigned per week (twelve across the Fall 2025 term); and, near the start of the term, a recitation section reviewing the probability background the course assumes. The term ends with a final exam. None of the homework problems, handwritten notes, or exam questions themselves are part of this chapter's source material — the home pages only link to them.

The sequence of topics across the term

The Fall 2025 schedule is the most complete of the three home pages read for this chapter, and its week-by-week lecture list is the clearest record of how the course orders its material. Grouping consecutive weeks by the topic they visit (a grouping made for readability here, not a division the source itself names) gives the following arc:

Weeks 1–2 — orientation. Lecture 1, Introduction; Lecture 2, Probability; Lecture 3, Estimation; a recitation reviewing probability.

Weeks 3–4 — sufficiency and exponential families. Lecture 4, Sufficiency; Lecture 5, Exponential Families (given a second lecture the following week); Lecture 7, Completeness.

Weeks 5–8 — the estimation-theory core. Lecture 8, Unbiased Estimation; Lecture 9, Score and Fisher Information; Lecture 10, Bayes Estimation; Lecture 11, Interpretation and Choice of Prior; Lecture 12, Bayesian Computation; Lecture 13, the James–Stein Estimator; Lecture 14, Minimax Estimation.

Weeks 8–11 — hypothesis testing. Lecture 15, Hypothesis Testing; Lecture 16, Testing with One Parameter; Lecture 17, p-values and Confidence Intervals; Lecture 18, Testing with Nuisance Parameters; Lectures 19–20, Testing in Linear Models (two lectures).

Weeks 11–13 — asymptotics and likelihood. Lecture 21, Asymptotics; Lecture 22, Maximum Likelihood Estimation; Lecture 23, MLE Consistency; Lecture 24, Likelihood-Based Inference.

Weeks 14–15 — resampling and multiple comparisons. Lecture 25, Bootstrap; Lecture 26, Multiple Testing (given across two class meetings).

Week 17 — final exam, 3–6pm.

Twelve homework sets are interleaved through weeks 3–12, each posted the week after the lectures it draws on. The Fall 2025 term's second home page (served from a units/ path on the same site) records the same course but only as far as Homework 1 in week 3, with slightly different Gradescope and EdStem course numbers than the main page — evidently an earlier snapshot of the same offering rather than a different course. The Fall 2026 home page, read at conversion time, carries the same course description and the same four resource links (syllabus, Gradescope, EdStem, bCourses) but no populated schedule yet — its schedule section was still an empty placeholder.

Sources

  • Fall 2025 course home page — docs/statistics/berkeley/stat210a/fall-2025/home.md (converted from berkeley-stat210a/fall-2025/index.html): course description, undergraduate-enrollment note, resource links, and the full Week 1–17 schedule used above.
  • Fall 2025 units-section home page — docs/statistics/berkeley/stat210a/fall-2025/units/home.md (converted from berkeley-stat210a/fall-2025/units/index.html): a partial duplicate of the same term, schedule only through Homework 1 (week 3), used above to flag it as an earlier snapshot.
  • Fall 2026 course home page — docs/statistics/berkeley/stat210a/fall-2026/home.md (converted from berkeley-stat210a/fall-2026/index.qmd): course description and resource links for the next offering; its schedule block was unpopulated.
  • Referred to by these pages but not contained in them, and so not covered here: the syllabus page, the per-lecture "reader" pages and handwritten notes for each of the 26 lectures, the recitation 1 probability-review PDF, the twelve homework problem sets and their LaTeX sources, the undergraduate-preparation FAQ, and the old-exams page.

← 18. Hypothesis Testing and Neyman-Pearson · Contents · 20. Statistics as Inductive Reasoning →