Skip to content

Lecture 1 exercises and typo fixes in Lectures 1-3 - #3

Merged
wiso merged 3 commits into
masterfrom
lectures/exercises-and-typos
Sep 26, 2026
Merged

wiso merged 3 commits into
masterfrom
lectures/exercises-and-typos

Conversation

@wiso

@wiso wiso commented Sep 26, 2026

Copy link
Copy Markdown
Owner

Summary

  • Lecture 1: three new exercise cells, without solutions:
    • The distribution of the p-value (after the question on the p-value distribution under H0): gaussian vs Poisson toys, why discrete tests are conservative.
    • Categorization pays off (after the median expected significance exercise): $Z_A$ per category, merged, and combined with a joint likelihood; additivity of $-2\ln\lambda$ on the Asimov dataset.
    • Bias of maximum likelihood estimators (after the $\sqrt{s^2}$ bias example): $\hat\tau=\bar t$ unbiased, $\hat\lambda=1/\bar t$ biased.
  • Lectures 1-3: spelling and grammar fixes (Exercize, explicitely, hypotesis, significace, "than" → "then", "Let find" → "Let's find", ...), correct ROOT class names in the text (AsymptoticCalculator, SetOneSidedDiscovery), and rename get_confiderence_poisson → get_confidence_poisson (definition and both call sites).

Only markdown text, comments and that one function name change; no logic changes.

Test plan

  • All code cells compile
  • aspell on the markdown/comments reports only identifiers
  • CI runs the modified notebooks

🤖 Generated with Claude Code

wiso and others added 2 commits September 26, 2026 23:34
… Lecture 1

Three new exercise cells, without solutions: the distribution of the
p-value under H0 (continuous vs discrete counts), the gain from
categorizing and combining channels, and the bias of the maximum
likelihood estimator of an exponential rate.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Correct misspellings (Exercize, explicitely, hypotesis, ...), wrong
ROOT class names in the text (AsymtoticCalculator,
SetOneSideDiscovery) and evident grammar mistakes. Rename
get_confiderence_poisson to get_confidence_poisson.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Copilot AI lite review requested due to automatic review settings September 26, 2026 21:34

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot review overview

🟡 Changes recommended

One moderate correctness issue and several remaining prose issues are unresolved.

Review effort: Lite
Findings: 1 Low severity

Open (1)
What changed in this PR

Adds three Lecture 1 exercises and corrects spelling, grammar, ROOT references, and a helper-function name across Lectures 1–3.

Changes:

  • Added exercises on p-value distributions, categorization, and MLE bias.
  • Corrected lecture prose and comments.
  • Renamed get_confiderence_poisson consistently.
File Review notes
Lecture3.ipynb Remaining grammar and wording issues at lines 976/2430, 993, 1010, and 1947.
Lecture2.ipynb Remaining fragment, notation ambiguity, and subject–verb agreement issues at lines 317, 808, and 812.
Lecture1.ipynb The MLE bias result should state the required condition (n>1) at line 536.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment thread Lecture3.ipynb Outdated
Fix the remaining grammar issues flagged in review, use lambda_up
(not n_up) for the upper edge of the excluded region, and state that
the bias of 1/t-bar is only defined for n > 1.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@wiso
wiso merged commit d795175 into master Sep 26, 2026
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants