Exploring NFL Data with nflscrapR

Exploring NFL Data with nflscrapR

Abstract

The current state of football analytics is heavily based on proprietary and potentially biased subjective data. Using the ‘nflscrapR’ package in R, I will demonstrate the type of reproducible research one can conduct with publicly available NFL data. Key concepts in football analytics research will be covered such as a comparison of the value of rushing and passing plays with expected points, as well as analyzing the most impactful plays with win probability.

Date
Location
Pittsburgh, PA
Avatar
Ron Yurko
PhD Student in Statistics & Data Science

My research interests include developing selective inference methodology for applications in statistical genetics and genomics, as well as clustering problems and research on statistics in sports.