Sports analytics: variáveis significantes na seleção de quarterbacks na NFL

Abstract

Given the importance of the quarterback for the football league teams - the NFL - from the United States of America, it is increasingly important to know which variables should be taken into account at the time of the draft. This research aims to verify which variables, among those measured throughout his career at the university and in the combine, predict the quarterback's rating in the NFL. The research was conducted with official data collected from secondary sources and multivariate data analysis was used, specifically multiple regression, to measure the relationship between the dependent variable and the independent variables. It was found that the performance variables currently taken into account in the selection of quarterbacks do not present significance in predicting the performance of athletes in the professional. From the results presented it is concluded that the quarterback's performance at the Combine and his performance history in College games do not significantly influence his performance in the NFL. Evidencing that analyzing only performance variables when recruiting a quarterback may not be enough.