Empirical Sports Blog

The Value of a Zone Start

There has been a back and forth going between Tyler Dellow of mc79hockey and David Johnson of HockeyAnalysis.com about Zone Start % (ZS%) and it’s impact on play and, in particular, the impact of ZS% on Fenwick For % (FF%) or Corsi For % (CF%).  There discussion so far is here (Dellow), here (Johnson) and here (Dellow)..   I appreciate the work of both but I prefer to think of what is gained by an individual  zone start.  Bruce McCurdy is on the right track, in  […]



Total Hockey Rating (THoR) results through 04/14/13

The THoR page (http://www.statsportsconsulting.com/thor) has the latest set of Even Strength ratings for the top 150 players.  I’ll give some commentary below.  Since MIT Sloan, we have added rink effects for each rink to the rink effects for shots and a score effect when the score has a differential of 2 or more.  The former aims to reduce bias in recording of RTSS events while the latter is indicative of changes of style of play according to the score. We got some good feedback at  […]



2013 MIT Sloan Sports Analytics Conference

2013 MIT Sloan Sports Analytics Conference

We are very fortunate a paper that I wrote with a former student, Jim Curro, accepted to the MIT Sloan Sports Analytics Conference Research Paper Competition.  The paper presents a  new ratings system which we think is an improvement over the current approaches.  It creates a two-way (offense and defense combined) rating that isolates the impact of an individual player by adjusting for home ice, the quality of competition, the quality of teammates and where a player starts their shifts.  We assess the impact of a player  […]



Going First in NHL Shootout: Postscript

A couple weeks ago I made available some work we did on the NHL shootout regarding whether there is an advantage to going first or second in the shootout.  This is a postscript to that post.Our analysis found that there was not an advantage to going first. This prompted some interest and some queries. Based on these, I’ve done some additional analysis and I want to share those. First, Bruce McCurdy of the Edmonton Journal wanted to know about whether there was a difference if the shootout  […]



Going First in NHL Shootout: A Statistical Analysis

Going First in NHL Shootout: A Statistical Analysis

With the end of the NHL lockout and the impending return of hockey, we thought we would take another look at NHL shootouts.  (The last time around we looked at the ability of goalies and shooters and found that there was nothing but randomness.  That post is HERE.)   Our focus this time around is to look at whether or not a team goes first matters.  As most readers of this post will know, the home team has the choice of going first or second  […]



More on NHL Faceoffs

More on NHL Faceoffs

This past Spring, two students of Schuckers did undergraduate honors theses at St. Lawrence analyzing NHL data.  Tom Pasquali who is now a graduate student in Statistics at Villanova University focused on faceoffs while another student, Jim Curro (now a graduate student in Statistics at Iowa State), did some work on player ratings.  In the NHL faceoff analysis that is linked below, we used primarily Tom’s work but also a portion of Jim’s work.  We analyzed over 200,000 faceoffs over three NHL regular seasons (2008-9,  […]



Article on US Division I College Hockey Attendance

Article on US Division I College Hockey Attendance

Recently I got asked by the guys at WI to look at the factors that influence a college hockey teams attendance.  One of my current students at St. Lawrence knows the college hockey landscape quite well so I asked Zach Nelson to work on this project with me.   For that analysis we looked at a variety of season level metrics for all of the US Division I hockey programs over the last 10 years.  Most of those metrics focused on the things that teams  […]



NHL Shot Probability Maps

NHL Shot Probability Maps

I recently made some league-wide shot probability maps based upon the 2009-10 NHL regular seasons.  Each map is of a particular shot type and strength of the shooting team.  The strength of the shooting team is whether they were at even strength, on the power play or were shorthanded.  The maps are limited to shots taken in the offensive zone.  Most of the methodology is the same as what is found in the DIGR paper.  I did some non-parametric smoothing using the LOESS function in  […]



MIT SSAC Hockey Panel (Video)

MIT SSAC Hockey Panel (Video)

Video of my appearance at the MIT Sloan Sports Analytics Conference Hockey Panel is now available.  Another panelists include Brian Burke, (GM for the Toronto Maple Leafs), Peter Chiarelli (GM for the Boston Bruins), Mike Milbury (NHL TV Analyst), Kathryn Tappen (TV host) and Tony Amonte (former NHL All-Star).     http://www.sloansportsconference.com/?p=4550 Here is the first of my postscripts on that panel.   Tweet



MIT Sloan Postscript 1: Faceoffs

MIT Sloan Postscript 1: Faceoffs

I attended the 2012 MIT Sloan Sports Analytics Conference last weekend in Boston. Additionally, I gave a poster and was invited to be part of the Hockey Analytics panel with Mike Milbury, Tony Amonte, Peter Chiarell and Brian Burke. NHL.com had a write-up of the panel here. I’m going to put together some posts/comments on that panel and some of the topics that came up. The first of these is the topic of faceoffs. I said in the panel that it takes an additional 100  […]