Applied Multivariate Statistical Analysis in Sports: A Case of Boxing

The purpose of this paper is to develop a multivariate statistical model for boxing matches. The model can estimate which factors affect match outcomes more effectively. This research employs a logistic regression model in which boxing match outcome, a dichotomous variable is used as a dependent variable. This study suggests that among a variety of independent variables, win/loss ratio, use of different punching techniques and state of mind prior to the match appear to play an important role in determining the match outcome.