Main Article Content
A number of methods have been proposed for predicting game winners in the National Collegiate Athletic Association’s (NCAA) annual men’s college basketball championship tournament. Since 1985, more than 70% of the teams in the fourth, fifth, and sixth rounds of the tournament have been high-seeded teams (i.e., teams assigned seeds of one, two, or three); a method that can accurately compare two such teams is often necessary to predict games in these rounds. This paper statistically analyzes tournaments from 1985 to 2009. A key finding is that there is an insignificant difference between the historical win percentages of high-seeded teams in each of the fourth, fifth, and sixth tournament rounds, which implies that choosing the higher seed to win games between these seeds does not provide accurate predictions in these rounds, and alternate predictors or methods should be sought. Implications on gambling point spreads are discussed.