Adjusted Plus-Minus
Adjusted Plus-Minus (also known as APM or Adjusted +/-) is a measure of a basketball player's total effectiveness, independent of box score statistics. It was invented in 2004 by APBRmetrician Dan T. Rosenbaum, at the time a professor of economics at UNC Greensboro. Through a complicated regression formula, APM reflects the impact of each player on his team’s bottom line (scoring margin per 100 possessions), after controlling statistically for the strength of every teammate and every opponent during each minute he’s on the court.
Due to the nature of regressing on such small sample sizes, APM can be an extremely volatile metric; the best players in one season can turn up as negative the next season despite similar box-score stats. That's why Rosenbaum advocated balancing "pure APM" (that is, APM based solely on the regressions) with what he called Statistical Plus-Minus, a regression of pure APM on boxscore stats that still showed a player's true value better than existing metrics like TENDEX, Wins Produced, and PER, but also was not subject to the large standard errors and wild fluctuations of pure APM (boxscore stats are relatively stable from year to year). In Rosenbaum's mind, a combination of pure and statistical +/- (each weighted by the degree of standard error in the pure APM estimate) would give the clearest picture of a player's on-court performance.
External links
- Adjusted Plus-Minus: An Idea Whose Time Has Come
- Meet Adjusted Plus/Minus
- Calculating Adjusted Plus/Minus
- Measuring How NBA Players Help Their Teams Win (Dan Rosenbaum's article in which he essentially "invents" APM)
- Washington Times article on WINVAL, a precursor to APM
- APBRmetrics search on APM
