Theory

Theory posts focus on musings based on statistical evidence, intended as proposals for discussion, debate, and/or further analysis.

The Defensive Shell is a good idea in theory. Unfortunately, it doesn’t work.

garik16 Theory Tags: , 5 Comments

The results of score effects are pretty basic hockey analytics knowledge at this point.  Teams down in goals tend to take more shots, while teams up tend to take less, with the effect becoming larger as the game goes on.

We often explain this effect by saying teams go into a “defensive shell”, playing extremely conservative on offense to avoid easy opponent scoring opportunities, at the cost of more time in the team’s defensive zone.  It is of course, not a one team effect either – we often emphasize that the other team is taking greater risks as well to try and score, which is why the shots taken by the team with the lead go in at a higher rate than normal.    That said, it’s pretty much accepted that going into a shell would be a losing strategy for a team to attempt over a whole game, which is why teams don’t attempt this strategy for a full game. Continue reading →

Draft & Develop: How analytics can be combined with qualitative scouting

Garret Hohl Theory Tags: , , , Leave a comment

NHLe1

The graph above represents how some may look at and use hockey statistics; the better a player performs in a statistic equates to more skill. This practice can be found in league equivalencies -now more commonly known as NHL equivalencies (or NHLe)- originally contrived here by Gabriel Desjardins.

In truth, almost all of us can be guilty of this at one point or another, like when using evidence like “Player A has a better Corsi%; therefore, he is pushes the play better”. Most reasonably understand that this is not how it works, but it is not discussed often enough. These tools are used to show average expected outcomes. The output is not the only possible outcome.  Continue reading →

Adjusted Possession Measures

mbmccurdy Theory Tags: , , 9 Comments

A little while ago I wrote an article at SensStats discussing score effects and suggesting a new formula which we might use to compute score-adjusted Fenwick. This article addresses several interesting questions and new avenues that were suggested to me by various commenters.

  1. The method in the above-linked article simultaneously adjusts for score and for venue (that is, home vs away). It’s interesting to estimate the relative importance of these two factors. As we’ll see, it turns out that adjusting for score effects is dramatically more important than adjusting for venue effects.
  2. We might consider adjusted corsi instead of adjusted fenwick; it turns out that adjusted corsi is a better predictor of future success than adjusted fenwick at all sample sizes.
  3. Most interestingly, we might consider how score effects vary over time, and see if we can create a score-adjusted possession measure that takes this variation into account. We find here that performing such adjustments is indistinguishable in predictivity from the naive score-adjustments already considered.

Several people have pointed out that score effects have a strong time-dependence. At least as far back as 2011, Gabriel Desjardins (@behindthenet) noted the effect and readers with keener memories than me will no doubt remember still earlier examples. Just last week, Fangda Li (@fangdali1) wrote an article arguing that score effects play virtually no role outside of the third period. This article will show that, while score effects are magnified as the game wears on, time-adjustment for possession calculations is not justified. Continue reading →

The State of Save Percentage

Garret Hohl Theory Tags: , , , , 1 Comment

Image from Wikimedia commons

Currently save percentage is the single best statistic for evaluating goaltenders… which is unfortunate as save percentage is extremely rudimentary and a suboptimal statistic.

There are two important factors for a statistic to be useful: that it impacts wins and the individual can either control or push the needle. Save percentage has both. Continue reading →

How much does matching competition matter on a team level?

garik16 NHL League-Wide Analysis, Theory Tags: , 2 Comments

This is certainly a terrible matchup – Matt Martin vs Alex Ovechkin – but it’s not an example really of terrible line management.

Quite frequently in talk about lines of a hockey team, you’ll find talk about how a certain team should be matching up certain lines against certain opponents.  For example, a recent comment to me on twitter stated roughly that: “As long as the Isles match-up the Frans Nielsen line with the Canes’ Eric Staal line, they’ll be in great shape” – as the Canes basically only had one quality line (the Staal line) at the time of that comment.  But as I replied on twitter, that isn’t quite right:

Competition, on a possession level, is pretty much a zero sum game in hockey.

Continue reading →

Remembering Dellow: A few graphs to convince you on Corsi

Garret Hohl Theory Tags: , , , , , 6 Comments

From Wikipedia Commons

Over the past year, I based a lot of research off of  former work by Tyler Dellow. It is a bit funny because I actually never read any of Dellow’s work until well after I started writing about underlying metrics in hockey. I knew of him, but mostly was brought up on Gabriel Desjardins, Eric Tulsky, Ben Wendorf (yes, Hockey-Graphs’ own Wendorff), and a few others. It is also a bit difficult now because Dellow’s website has gone dark with his hiring, which removed the work I quoted or built upon.

One Dellow article that will be severely missed is Two Graphs and 480 words will convince you on Corsi.

Dellow presented analytical data in simple and effective ways. It made understanding of complex concepts -such as regression in goal differentials- easy.

Continue reading →

What to Expect When You’re Expecting: Does Switching NHL Head Coaches Make a Difference?

Benjamin Wendorf NHL League-Wide Analysis, Theory Tags: , , , , , , , , , , 2 Comments
Bruce Boudreau

Photo by Matthew Miller, via Wikimedia Commons; altered by author

How good do you feel because your team has a new coach? I mean, really…it’s almost like a new-car smell. So many possibilities – This time, things will be different. With the exception of coaching changes due to disastrous, unexpected things, the typical hockey fan was ready for that moment, and were happy to see the coach go. But is that eagerness for change based on real results?

Continue reading →

Scoring talent influence on goal differentials and statistical double dipping

Garret Hohl Theory Tags: , , , , , , Leave a comment

Screen shot 2014-09-09 at 1.20.24 AM

In August, I wrote an article on how you can translate Corsi differential values in terms of the average expected goal differential given for a players of similar average ice time.

In the article, I used an example of how this information could be used:

For example, Matt Halischuk and Eric Tangradi are two players who averaged 4th line minutes on the Winnipeg Jets. Tangradi finished the season with a 53.9% Corsi, while Halischuk was at 44.0%. Over the span of a season, forwards with those Corsi% would be expected to have on average of -1.04 and a -4.77 goal differential respectively. Therefore, on average, a 53.9% Corsi fourth line forward is worth 3.73 goals more than a 44.0% Corsi forward. Another option is comparing these players to the 46.8% Corsi% of an average fourth line player. The goal differentials can then be used to estimate win values using Pythagorean relationships.

There is a caveat with using raw Corsi% to estimate goal differentials; all effects -such as zone starts- still apply. The estimated goal differentials would be no more predictive than Corsi is; however, you can now easily and more accurately measure Corsi impact in terms of goals and wins.

Now, I used the example of Halischuk and Tangradi for a few reasons. The main one being that they are familiar to me as Winnipeg Jets players. They are two fourth line players that have experienced similar usage but have very polar opposite shot metrics. But, there is another reason… an interesting one.

Continue reading →

To Draft or Not To Draft Goalies – Not Really the Right Question

garik16 Theory Tags: , , , , 1 Comment

On Monday, Kyle Alexander and CAustin (aka the Puckologist) wrote a post on Raw Charge titled “It’s still okay for an NHL team to draft goaltenders.”  This is a topic that isn’t exactly new in the hockey analytics community – on this site alone Garret and myself have written a few posts about how unpredictable goalies are and the general consensus in the hockey analytics community being that goalies are simply not worth drafting in the early rounds of the draft, due to the variability on their results compared to other skaters (particularly forwards).

The Raw Charge guys in their post don’t totally disagree, but do think the talk of avoiding goalies is a bit exaggerated by some, concluding:

However, the gap between goalie drafting and forward drafting isn’t nearly as stark as it’s been made out to be. It’s much more worthwhile to make drafting and development at all positions better than to attempt to specialize in elite forwards to the exclusion of other positions.

Essentially, the Raw Charge guys argue:
1.  The Gap between skaters and goalies’ success and failure rates isn’t as big as people think – most evaluative measures used in such studies disfavor goalies by using metrics such as GP by a certain age, where goalies rarely get opportunities to meet such thresholds.
2.  The response to whatever gap there actually is should be to try and improve goalie evaluation – similar to how Swedish and Finnish goalie federations’ improved early goalie training to improve their goalie crop – rather than to eschew goalies altogether.
3.  The failure of goalies may also have to do with poor development processes rather than bad evaluation.

While all three points do have merit, I think they’re both quite a bit overstated.

Continue reading →

An early look into some of the new numbers available

Garret Hohl Theory Tags: , , Leave a comment

From Wikipedia Commons: A graph showing the minimum value of Pearson’s correlation coefficient that is significantly different from zero at the 0.05 level, for a given sample size.

There are two new and very exciting frontiers being explored by the hockey analytics blogosphere. There is the manual tracking of zonal statistics, such as zone entries and exits. This area of research was first pioneered by Eric Tulsky and Corey Sznajder. Then there is the splicing of Corsi into microstates, such as looking at shot attempt differentials momentarily after face off wins or loses in particular zones. The early workers on these numbers were Tyler Delow and Muneeb Alam.
(side note: it should not be a surprise that one of each group was recently picked up by a NHL team this summer)

I recently was able to get data from the non-NHL hires named above (and will enjoy their contact while I can until they are picked up too). Sznajder provided me with zone entry and exit data for just over 60% of the NHL. If you would like to check out his project and contribute, check this link. Alam sent over shot attempt events 10 seconds after a defensive zone face off, which was further separated into wins and losses.

I originally received this data for study of the Jets and noticed what appeared to the eye to be a relationship, and wished to delve in further.

Continue reading →