Data Mining the Play-by-Play: Assessing and Applying NHL Performance Metrics Using Statistical Methods

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Supplemental Files: 

Creator: 

Diaz-Papkovich, Alexandr

Date: 

2015

Abstract: 

Hockey statistics are traditionally simple with limited analytical value, especially for individual assessment. The National Hockey League provides Play-By- Play and Time-On-Ice files for every game, recording game events and players present during them. These are combined to derive Corsi, Fenwick, and shot differentials, now commonly used in the hockey analytics world. Using regression and data visualization we examined their value in explaining win percentage and goal percentage, demonstrating the value of full-strength tied Corsi particularly. We also examined the effects of score on shot attempts, and the effects of special teams and home advantage on win percentage. Finally, we created a binary transaction database of players and Corsi events and applied association rule learning to clearly measure individual performance and player chemistry, demonstrating significant potential for use in management and coaching.

Subject: 

Statistics

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Master of Science: 
M.Sc.

Thesis Degree Level: 

Master's

Thesis Degree Discipline: 

Probability and Statistics

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).