La. Craig et Ar. Hall, TRYING OUT FOR THE TEAM - DO EXHIBITIONS MATTER - EVIDENCE FROM THE NATIONAL-FOOTBALL-LEAGUE, Journal of the American Statistical Association, 89(427), 1994, pp. 1091-1099
A recent article in Sports illustrated argues that the National Footba
ll League (NFL) preseason schedule should be eliminated because the ga
mes are meaningless, feature subpar players, and are of no interest to
fans. In this article we challenge this view, using statistical techn
iques to analyze both the outcome of preseason games and their value a
s a predictor of regular season performance. Our analysis is based on
the application of a rank-order tournament model to the NFL labor mark
et. The model explains preseason results in terms of the competition f
or positions on teams. Two implications are that the outcome of presea
son games should reflect the labor market characteristics of the parti
cipating teams and that a team's preseason record should be positively
related to its regular season record. Both of these hypotheses are co
nsistent with our analysis of NFL data from 1970 through 1991.