MATH5806 Applied Regression — Anki deck

What it is

The card deck I built while taking UNSW's MATH5806 (Applied Regression Analysis): least squares and its matrix algebra, inference and intervals, residual diagnostics panel by panel, the GLM family — links, deviance, Wald and likelihood-ratio tests — logistic and Poisson regression, overdispersion, model selection (AIC/BIC/cross-validation), shrinkage, splines and GAMs.

What's inside

• 180 notes / 191 cards, tagged by topic (glm, diagnostics, logistic, deviance, modelselection, …).
• 64 R cards — the working statistician's R (lm/glm, confint vs confint.default, Pearson residuals, predict intervals, dpqr functions), syntax-highlighted; 21 interactive type-in cards that diff the line of R you type against the answer.
• Maths renders via Anki's built-in MathJax; nothing to install.
• Custom styled note types travel inside the .apkg and install on import.
• No review history — every card arrives fresh for your own schedule.

How the cards are written

One fact per card, interpretation first: read the summary(glm) output, turn a coefficient into a rate ratio, say why LOO-CV is high-variance — not formula recall. Notation follows Dobson (μ for the Poisson mean). Everything is phrased in my own words from my own study notes.

Pairs well with

My free statistics notes and solutions books at abaj.ai — the cards drill what the notes explain.