Fill in AIC/BIC section with detailed content and attributions#394
Fill in AIC/BIC section with detailed content and attributions#394d-morrison merged 8 commits intomainfrom
Conversation
Agent-Logs-Url: https://github.com/d-morrison/rme/sessions/b209bc39-88e2-4dc5-9a15-76f4be92c069 Co-authored-by: d-morrison <2474437+d-morrison@users.noreply.github.com>
Agent-Logs-Url: https://github.com/d-morrison/rme/sessions/b209bc39-88e2-4dc5-9a15-76f4be92c069 Co-authored-by: d-morrison <2474437+d-morrison@users.noreply.github.com>
Agent-Logs-Url: https://github.com/d-morrison/rme/sessions/264ec644-046b-4544-872b-1334b56bd97f Co-authored-by: d-morrison <2474437+d-morrison@users.noreply.github.com>
|
@copilot resolve merge conflicts |
…file Co-authored-by: d-morrison <2474437+d-morrison@users.noreply.github.com>
Built to branch |
There was a problem hiding this comment.
Pull request overview
Expands the course material on AIC/BIC model comparison (including formulas, conceptual interpretation, and attributions) and updates supporting bibliography/spellcheck artifacts.
Changes:
- Adds detailed AIC/BIC exposition in the linear regression goodness-of-fit section (formulas, conceptual breakdown, comparison table, interpretation guidance, speaker notes with historical citations).
- Adds Akaike (1974) and Schwarz (1978) entries to the bibliography.
- Adds “Kullback” and “Leibler” to the package WORDLIST.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
_sec_linreg_gof.qmd |
Expands AIC/BIC section content, adds formulas/interpretation, and adds attribution + historical notes. |
references.bib |
Adds bibliographic entries for Akaike (1974) and Schwarz (1978). |
inst/WORDLIST |
Adds spelling whitelist entries for “Kullback” and “Leibler”. |
| where $\ell(\hat\theta)$ is the log-likelihood evaluated at the | ||
| maximum-likelihood estimates $\hat\theta$, | ||
| $p$ is the number of estimated parameters | ||
| (including $\hat\sigma^2$ for Gaussian models), | ||
| and $n$ is the number of observations. |
There was a problem hiding this comment.
In @def-aic, the prose defines n as the number of observations, but n doesn’t appear in the AIC formula. This is confusing and also forces @def-bic to reference @def-aic for n. Consider defining only \ell(\hat\theta) and p in @def-aic, and defining n in @def-bic (or explicitly note that n is used in BIC, not AIC).
Linear-models-overview.qmdwith::::{#def-aic}and:::{#def-bic}definition divsreferences.bibinst/WORDLISTorigin/main(AIC/BIC content moved to_sec_linreg_gof.qmdsubfile)