Available Variables
Your Model
Predictors (X)
Variables that help predict proportions
Drop predictors here
Response (y)
What we predict
Drop response here
Beta regression for proportions
Exam pass rates are bounded between 0 and 1 — they're not binary (pass/fail) but continuous proportions. A student might answer 73% of questions correctly. That's not a count, not a binary outcome, and not unbounded.
Solution: Beta regression is designed for continuous data on the open interval (0, 1), where neither Gaussian nor Binomial applies.
This tutorial extends the GLM framework from the JonStats course to bounded proportions — material not covered in the original series.
Drag Proportion Correct to the Response zone on the right.
This is a continuous value between 0 and 1 — a key characteristic for Beta regression.
Variables that help predict proportions
Drop predictors here
What we predict
Drop response here