Dissertation/Thesis Abstract

Predicting the Success of Running Back Prospects in the National Football League
by Merritt, Kevin M., M.S., California State University, Long Beach, 2017, 103; 10287281
Abstract (Summary)

National Football League team’s analysts use statistics in a multitude of ways, including game planning, game day rosters, and incoming talent evaluation. Focusing on the running back position, we attempt to improve upon models designed to predict the future success of incoming collegiate players while introducing some models of our own. Focusing on running backs drafted from 1999 to 2013, we use data from the player’s college career, combine workouts, pro day workouts, and physical measurements. Using linear regression, recursive partitioning decision trees, principal component analysis, zero-inflated negative binomial regression, hurdle negative binomial regression, and zero-inflated truncated normal regression, we develop models for three different success criteria: a weighted combination of games played and started, yards per rushing attempt, and career yards from scrimmage.

Indexing (document details)
Advisor: Korosteleva, Olga
Commitee: Safer, Alan, Suaray, Kagba
School: California State University, Long Beach
Department: Mathematics and Statistics
School Location: United States -- California
Source: MAI 56/05M(E), Masters Abstracts International
Subjects: Statistics
Keywords: NFL, National football league, Predict, Running back, Statistics
Publication Number: 10287281
ISBN: 9780355097573
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy