Islanders Bits: About Last Night, and about Regression

Some quick hits while we sweep the ice with a smile on our face:

Last Night's Game: Recaps (and reader comments) from LHH | Newsday with some interesting quotes from Capuano, Nabokov and Cizikas | Philly Inquirer with Lavi's penchant for early timeouts | Philly.com with Jagr and Hartnell riffing. | Checking Line | IPB on the 3-6-1 Isles | Knight of Cups

Meanwhile, with back-to-backs this weekend and Al Montoya's injury sending him back to Long Island, Newsday has AHL Goalie of the Month Anders Nilsson on Anders Nilsson, and Capuano on Nino.

The Canadiens-Wild game was truly wild last night, this uncalled hook and belly-flop being one reason. This shootout tragedy being another.

And finally, a concept that's worth exploring for every hockey fan:

Kent Wilson is a Flames-centric writer who writes a lot of insightful things about the NHL overall. (I say this not just because he was one of the people who, like me, detected that Frans Nielsen was pretty important before Frans was cool.)

He writes all over the place and now Puck Daddy has him on the roll as well. Which will be interesting, because he goes deep into concepts that the average PD commenter, at least, doesn't have time for. But he did a great, approachable piece on regression in hockey, and with this year's once-first-place, now-not-playoff-bound Wild specifically. A sampling:

Minnesota's record was unlikely for a numbers of reasons. Not the least of which was the fact they were getting routinely outshot. In fact, despite boasting one of the best records in the league at the time, the Wild had surrendered 173 more shots on net at even strength than they had generated up to that point. They had also blocked 145 more shots than the opposition. Again, that's only at even strength.

Their total shots for/against (or "CORSI ratio") to that point was just .419, one of the worst in the league. Nevertheless, the underdog Wild were "finding ways to win," to borrow a cliché, so any skepticism was dismissed out of hand.

After all, pointing to the standings could readily silence any unbeliever.

Wilson frequently brings psychological concepts to this topic which -- with apologies to Tom Cruise and the nutjob ship he arrived on -- is helpful when understanding how humans view events:

Humans prefer patterns and causal chains to abstract notions of variance or probability. In fact, people tend to identify apparent patterns in randomness without effort and to fit noisy, complex events with tidy narratives that make them easier to understand and more coherent.

And also:

As Kahenman notes, some of these stories may even be true, but by and large the uncanny winning streaks and unsavory losing streaks that we see often have as much to do with the inscrutable ebb and flow of variance and probability as the team's true talent level.

Over a long enough timeline, a club's talent level will emerge, but over relatively small samples such as 10, 20, or ever 30 games, lousy teams can post a winning record and vice versa as a matter of chance.

If this at all interests you, I urge you to read the whole article -- as Kevin Schultz of IPB noted, this concept is helpful in poker -- and also to remember this: This isn't really about "stats guys" with their spreadsheets vs. "true fans" with their eyes. It's about ways to better understand the game and what is likely to happen in the future. Yes, some stats-centric fans are arrogant and frankly unapproachable. Likewise some "I know what I saw" fans who are sure that the sea was angry that day.

In the interests of critical thinking, in the spirit of the liberal arts, in the desire not to live in a bubble or echo chamber, it's so helpful to consider what all perspectives have to offer.

Why a person looking for explanation or professing opinion wouldn't leave room for both the eyes and the quantitative data is beyond me. Or put it this way: If your team is in first place in early December, wouldn't you like some kind of lens on whether it was likely to continue (i.e. "sustainable," as in the Blues' performance even after a 6-7 start) or if it was likely to come back to earth plenty (as in this year's Wild, last year's Stars, the previous year's Avalanche)?

When I repeat "small sample" like a broken record (I wish there was a more fun term), it's not to be a Debbie Downer raining on parades during good times or be an apologist during the slumps. It's to remind ourselves, we humans, that even Jeff Tambellini has an NHL hat trick to his name.