Accessible Unlicensed Requires Authentication Published by De Gruyter May 3, 2011

Stratified Odds Ratios for Evaluating NBA Players Based on their Plus/Minus Statistics

Douglas M Okamoto

In this paper, I estimate adjusted odds ratios by fitting stratified logistic regression models to binary response variables, games won or lost, with plus/minus statistics as explanatory variables. Adapted from ice hockey, the plus/minus statistic credits an NBA player one or more points whenever his team scores while he is on the basketball court. Conversely, the player is debited minus one or more points whenever the opposing team scores. Throughout the NBA season, the league’s better players are likely to have positive plus/minus statistics as reported by Yahoo!Sports and 82games.com. Crude or unadjusted odds ratios estimate the relative probabilities of a player having a positive plus/minus in a win, versus a negative plus/minus in a loss. Home and away games are twin strata with teams playing 41 home games and 41 road games during an 82-game regular season. Stratum-specific odds ratios vary because some players perform better at home than on the road and vice versa. In order to adjust for home court advantage, stratified odds ratios and their 95 percent confidence intervals are estimated for each of the Los Angeles Lakers during the 2009–2010 regular season.

Published Online: 2011-5-3

©2011 Walter de Gruyter GmbH & Co. KG, Berlin/Boston