Biggest Regression Candidates

Mark Barbour (@18sktrs,

In this article I’m going to talk about the skaters who have scored either too many or too few goals during the last 20 team games. WARNING: I’ve got bad news about one of your favourite skaters (probably). I also have some good news. Let’s get into it.

The data for this article were pulled from Natural Stat Trick and include games played on or before November 29, 2022.

Regression – What Are We Talking About Here?

I want to be clear about what I mean by “regression” in this article. I’m using that term to refer to the output of a linear regression model. The “predicted” goals that I talk about were predicted by that model.

With that out of the way, let’s look at the candidates for “positive” and “negative” regression. Note that only skaters who play at the forward positions are included in this analysis. As noted above, the data are taken from the last 20 team games for each skater.

Biggest Over/Under Goal Scorers

The plot below is based on the difference between a skater’s actual goals and his predicted goals. The line represents the density of skaters at each point between -6 goals under predicted to +6 goals over predicted. Most skaters are clustered around “0.0” which means their actual goals are close to their predicted goals.

I highlighted 3 skaters at each end of the distribution – the skaters on the left scored fewer goals than predicted and the skaters on the right scored more goals than predicted.

Let’s start with the skaters who have scored too many goals and could see some “negative regression”.

  • Nick Suzuki has probably scored too many goals. He’s a fine skater but some of his recent production is unlikely to continue. Sell high if you can.
  • Bo Horvat is tied for 2nd in NHL goal scoring. He probably won’t keep up that pace. Horvat did have the 10th highest predicted goals over the last 20 games, which is pretty good. I see that his time-on-ice is trending down which could affect his goal scoring if the trend continues. I would probably just hold Horvat unless I could find a very eager buyer.
  • Jason Robertson has everyone’s attention right now as he’s scored the most goals in the NHL. The bad news: his predicted goals were less than his actual goals. Now that you’re angry at the model, here’s the good news: Robertson had the most predicted goals in the NHL over the last 20 games, putting him on pace for 57 goals in 82 games. Hold on to him unless you can get an absolute haul. I doubt that you can acquire him for a reasonable price at the moment.
  • FYI, the skater with the second highest predicted goals during the last 20 games was Tage Thompson. He was virtually tied with Robertson on a predicted 57-goal pace. He’s shooting up my personal skater projections and this might be a case where my projections are still catching up to where Thompson is heading. Unlike Jason Robertson, I feel like you might find someone who’s still a little skeptical about Tage Thompson. There could be an opportunity here to acquire him at a reasonable price.

Now on to the “positive regression”!

  • Nathan MacKinnon has scored only 6 goals this season. I expected more from him, and so did the regression model. His predicted goals were closer to 10-11 during the last 20 games. Buy low if you can? I mean … this is Nathan Mackinnon we’re talking about.
  • My regression models usually expect Brady Tkachuk to score a lot of goals, and this time was no different. Tkachuk had the 5th highest predicted goals during the last 20 games. He’s a skater who’s always around the net but his actual goals never catch up with his chances. I try to incorporate “finishing ability” into my regression models but Tkachuk is so dominant in things like shots and scoring chances that he kinda breaks the model. Will Tkachuk eventually score on more of his chances? I don’t know. Coming into this season I was optimistic that he was improving. In 2020-21 Tkachuk’s actual goals equaled only 68% of his expected goals (as determined by Natural Stat Trick). Then in 2021-22 his actual goals equaled 87% of his expected goals. This looked like progress! Unfortunately, though, he’s back down to 68% again in the first 21 games of this season. I hope that we see some “positive regression” for Brady, but I’m not convinced that it will happen. In the meantime, he’s a great skater to have on your fantasy team just the way he is.
  • The last name here is Sam Bennett. He’s scored only 4 goals in his last 20 games. His predicted goals during that time were closer to 8, which would put him at just under a 32-goal pace (matching his performance from last season). My personal skater projections are still high on Bennett (he’s actually rising in the rankings if you can believe it). Bennett is probably a good buy low target right now.

The End Of The Article

Do you have an idea for some interesting data analysis? Let me know and maybe I’ll turn your idea into an article. Cheers!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: