Sports Magazine

Attempting to Establish a Link Between Specific On-ice Metrics and Scoring-chances

By Kicks @Chrisboucher73
Establishing a direct link between specific events that occur on the ice and scoring-chances will always remain among the main objectives in hockey analytics.
What plays create scoring-chances?
Through 4 years of tracking every puck-possession events from every Montreal Canadiens game, I have attempted to find a link between specific plays I track, and scoring-chances. Those plays that impact scoring-chances include offensive-zone passes off of the rush, offensive-zone east/west passes, offensive-zone passes to the slot, offensive-zone loose-puck recoveries (off of dumps, broken plays, and rebounds), shots, and deflections. The more players produced within these metrics, the more scoring-chances they tended to produce.
Only even-strength events are included here. These graphs contain data from both the 2013-14 regular season and the 2014 playoffs. A list of all the events tracked within my system can be found here.
REGRESSION ANALYSIS
Every point within the graph represents a Montreal Canadiens player. A player is credited with a scoring-chances when he is directly involved in a play that either produced an attempted shot, or deflection from the slot.
R-squared is a statistical measure of how close the data are to the fitted regression line.
The definition of R-squared is fairly straight-forward; it is the percentage of the response variable variation that is explained by a linear model. Or:
R-squared = Explained variation / Total variation
R-squared is always between 0 and 1:
  • 0 indicates that the model explains none of the variability of the response data around its mean.
  • 1 indicates that the model explains all the variability of the response data around its mean.
In general, the higher the R-squared, the better the model fits the data.
   -Jim Frost
Expressed as simply as possible (maybe even too simply), this graph tells us that 89.59% of scoring-chances the players included here produced directly related to the number of scoring-plays they produced.

EVEN-STRENGTH SCORING PLAYS PER-60
Among defensemen, Nathan Beaulieu (SSS) produced the most ES scoring-plays per-
60; followed closely by PK Subban, and Andrei Markov.  Lars Eller produced the most scoring-plays per-60 among centres, while Brendan Gallagher, and Max Pacioretty produced the most among wingers.

EVEN-STRENGTH SCORING-CHANCES PER-60
Beaulieu also produced the most scoring-chances per-60 among Habs d-men; followed closely by Subban and Markov. David Desharnais produced slightly more scoring-chances per-60 among centres than Eller, while Thomas Vanek actually produced the most scoring-chances per-60 among Habs players; followed by Gallagher and Pacioretty.

EVEN-STRENGTH POINTS PER-60
Mike Weaver actually led all Montreal defensemen in even-strength points per-60. That said, Weaver's smaller sample size within this metric explains the anomaly. Among defensemen with substantial sample sizes, Subban and Markov are the Habs top back-end point-producers at even-strength.
Desharnais led all centres in ES points per-60, while Vanek, Dale Weise, (SSS) Max Paciorety, and Brendan Gallagher were the Habs top point-producers among wingers.


Back to Featured Articles on Logo Paperblog