🐻⬇️🏀

Model Card

RAPM on the per-segment margin of defensive rebounds (own minus opponent per 100 possessions), fit only on games whose play-by-play defensive rebounds equal the box exactly. The ridge penalty is chosen by game-level cross-validation. Positive values mean a player's minutes raise their team's defensive rebounds relative to the opponent's. On nba 2024-25 (in-sample event Elo) neither method found signal in defensive rebounds. Held-out check (date split: fit before a date, score later segments; ncaam 2022-23 and 2023-24, ncaaw 2023-24): correlation with the actual per-segment margin 0.056-0.091 for this model, 0.029-0.066 for the event Elo it replaces. Small in absolute terms: a segment holds about one such event.

Validation is computed for team models, APM, RAPM and the event models. This page shows output coverage and site placement for this model.

Selected League / Season

Change league with the League selector at the top of the page.

Held-out player predictions

Plot Defensive Rebounds RAPM against any counting stat (one point per player, every season with a served list).

No current held-out results for this selection. Held-out player validation covers APM, RAPM and the event models.