A 2015 NCHC Prediction

My 2015 NCHC prediction says North Dakota is the team to beat.

If you’re just tuning in, we’re working toward making a 2015 NCHC prediction. So far, we’ve developed a model that explains the primary inputs into how teams earn points. Then, we tested the model on previous seasons and other leagues. Everything is holding up, and we have a good idea of the strengths and weaknesses of the model. Now we get to the truly hard part – generating and estimation of how well we expect teams to perform this year on three measures – shooting percentage, save percentage, and possession time.

I’ve collected individual-level data on all NCHC players from 2013-14, including goals, shots, sh%, sv% and a derived possession-share (individual shots/all shots). Before I got any further, I just want to say: DENVER and COLORADO COLLEGE, GET YOUR ACT TOGETHER. All other schools provide individual-level conference data on goals, shots, blocks, and a host of other measures. CC links to an outside website, and Denver offers one PDF on season data. I really wish the league office would get some standards around this. But I’ll move on.

We’re going to adjust sh%, sv% and possession for each team based on what we know about roster changes, particularly about who is returning and who has left. To do this, I have to make some assumptions about players and teams. I’ll try to keep these as safe as possible:

Assumptions:

  • Most returning players will perform about the same as they did last year in sh% and sv%. At a team level, this will even out in the aggregate.
  • Teams with no coaching changes and stable possession over time will have similar possession in 2015. Adjustments will be made based on loss of a high-shooting player or an increased role of a returning player, as well as an assumed regression toward the mean.
  • New players will perform at the average of last year’s new players. We’re not sure how junior or high school hockey translates in NCAA talent, and even if it did, we don’t know how much any individual guy will play this year. So until they prove otherwise, they’re considered average.
  • Extreme outliers need to be moderated. If Nic Dowd or Josh Archibald were returning this year, I would tone them down based on expected regression toward the mean.

I tried to reduce subjectivity, but that’s not entirely possible. To deal with that, remember that all of these assumptions will be constrained, because there are a few constants that MUST be true in the model:

Constants:

  • NCHC shot% + save% will always equal 100%.
  • Furthermore, don’t expect Sh% to deviate much from just less than 10% and don’t expect save % deviate much from just more than 90%.
  • NCHC average possession is always 50% and possession ratio is always 1.00.
  • Total points will equal 336.

Finally, noise will happen, and I can’t predict it. That’s why we watch the games and they play the seasons. I’ll point out some specific noise producers at the end of this article. So without further ado, here we go.

First of all, let’s look at how shooters from each class within each team performed last season:

Colorado College 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14 Team
Sh% 9.80% 6.98% 7.05% 6.56% 7.74%
Poss. Share 30.36% 19.20% 23.21% 27.23% 100%
Avg. Shots 29.1 21.5 22.3 36.6 26.9
Avg. Goals 2.9 1.5 1.6 2.4 2.08
Count 7 6 7 5 25
Lose in 14-15 2 1 0 5 8

Denver 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 9.41% 9.84% 9.42% 4.92% 9.08%
Poss. Share 30.56% 18.46% 41.75% 9.23% 100%
Avg. Shots 22.4 20.3 39.4 30.5 27.5
Avg. Goals 2.1 2.0 3.7 1.5 2.5
Count 9 6 7 2 24
Lose in 14-15 0 2 0 2 4

Miami 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 8.18% 6.96% 8.56% 5.56% 7.60%
Poss. Share 14.93% 42.88% 34.87% 7.33% 100%
Avg. Shots 18.3 35.1 42.8 27.0 32.0
Avg. Goals 1.5 2.4 3.7 1.5 2.4
Count 6 9 6 2 23
Lose in 14-15 1 0 0 2 3

Minnesota-Duluth 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 9.51% 5.95% 14.45% 4.30% 8.83%
Poss. Share 33.67% 32.27% 22.15% 11.91% 100%
Avg. Shots 37.6 36.0 34.6 31.0 35.5
Avg. Goals 3.6 2.1 5.0 1.3 3.1
Count 7 7 5 3 22
Lose in 14-15 0 0 2 3 5

Nebraska-Omaha 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 10.98% 7.27% 16.99% 5.98% 9.87%
Poss. Share 19.74% 13.24% 24.79% 42.24% 100%
Avg. Shots 27.3 27.5 51.5 50.1 39.6
Avg. Goals 3.0 2.0 8.8 3.0 3.9
Count 6 4 4 7 21
Lose in 14-15 0 1 1 7 9

North Dakota 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 10.64% 9.39% 13.02% 11.63% 11.06%
Poss. Share 20.52% 35.66% 31.30% 12.52% 100%
Avg. Shots 20.1 40.8 30.7 28.7 29.8
Avg. Goals 2.1 2.8 4.0 3.3 3.3
Count 7 6 7 3 23
Lose in 14-15 1 1 0 3 5

St. Cloud State 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 5.33% 16.20% 5.19% 15.54% 12.46%
Poss. Share 10.74% 45.99% 22.06% 21.20% 100%
Avg. Shots 18.8 45.9 19.3 37.0 30.4
Avg. Goals 1.0 7.4 1.0 5.8 3.8
Count 4 7 8 4 23
Lose in 14-15 0 0 1 4 5

Western Michigan 13-14

Fr. 13-14 So. 13-14 Jr. 13-14 Sr. 13-14
Sh% 6.31% 8.71% 10.14% 15.38% 10.06%
Poss. Share 16.92% 40.24% 21.04% 21.80% 100%
Avg. Shots 13.9 44.0 27.6 35.8 28.5
Avg. Goals 0.9 3.8 2.8 5.5 2.9
Count 8 6 5 4 23
Lose in 14-15 0 0 1 4 5

And for good measure, let’s look at what every team loses for 2014-15, in terms of percentage of their team, but also in terms of shooting percentage of those departed players and the share of the possession they made up:

2014-15 NCHC Team Losses

Team % of team lost Lost Sh% Lost Poss.%
Colorado College 32.0% 7.11% 33.48%
Denver 16.7% 4.76% 9.53%
Miami 13.0% 5.08% 8.01%
Minnesota-Duluth 22.7% 2.58% 19.85%
Nebraska-Omaha 42.9% 9.30% 58.24%
North Dakota 21.7% 9.84% 26.64%
St. Cloud State 21.7% 14.94% 22.06%
Western Michigan 21.7% 12.92% 27.13%
NCHC Average 24.1% 8.31% 25.62%

Let’s pause for a second to digest all this. It appears UNO loses the most, but they lose mostly a senior class that didn’t perform very well (and one junior who performed better than possibly anyone in the league). Miami returns nearly its entire roster, for better or worse. SCSU and WMU lose some high-quality shooting. Meanwhile, Denver and Duluth cut some fat (relatively speaking). Also notable: UNO and UND will have high-performing sophomore classes, while SCSU’s and WMU’s same classes didn’t show much promise. One would expect our predictions to reflect these roster changes, factoring in the temporal trends we looked at on Tuesday.

Back to our predictive model. Let’s assume all the returning players will perform at about the rate they performed last season. Obviously this won’t be true down to the player, but at the aggregate, it should pan out – and I’ll just have to hope the team-level adjustments aren’t huge.

In addition, I’ll make the assumption that each team’s new players will perform at about the rate last year’s new players performed. For most teams, this tends not to matter hugely, because rosters are stacked this year and most freshman won’t play that much. The only teams for which it matters significantly is UNO, which has 11 incoming freshman.

Putting this all together, we have a rough approximation of what sh%, sv% and possession might look like for this NCHC season. Assuming we’re comfortable with these numbers, all we have to do is plug these numbers into the model, and we get:

2015 NCHC Expected Metrics

Team '14 Shot% '15 Shot% '14 Save% '15 Save% '14 Poss% '15 Poss% '15 Points* '15 Finish
North Dakota 11.06% 11.26% 91.41% 92.03% 48.38% 49.50% 48 1
Nebraska Omaha 9.87% 10.82% 89.22% 90.45% 56.49% 49.50% 41 2
Minnesota Duluth 8.83% 9.05% 89.83% 89.35% 53.17% 54.50% 36 3
St. Cloud State 12.46% 10.02% 91.14% 90.21% 49.15% 49.00% 36 3
Denver 9.08% 9.44% 92.87% 91.45% 44.81% 47.50% 36 3
Miami 7.60% 7.81% 88.90% 90.90% 50.55% 52.75% 34 6
Western Michigan 10.06% 8.68% 90.11% 90.45% 48.45% 48.50% 30 7
Colorado College 7.74% 8.31% 89.39% 89.72% 48.73% 48.75% 27 8
ALL NCHC 9.58% 9.43% 90.42% 90.57% 50.00% 50.00% 288
*All 14-15 expected points +-4.85

Does this make sense? Let’s discuss the data:

  • Colorado College: CC is a huge wildcard. They lost a fair number of guys, but they return some key players, too. Their goaltending is completely unknown, so I put them at league average for lack of a better predictor. I would assume their possession numbers get better with a new style of play (seems to be a general trend). That said, it’ll still be underwater, and shot% will still be low. But here’s hope for the future: The best talent CC has is all very young.
  • Denver: Let’s start with the most obvious change: No Sam Brittain. However, backup goalie Evan Cowley got a non-negligible amount of net time, and the numbers suggest he might be just as good as Brittain. In addition, I expect Denver’s possession to regress to the mean, but only slightly, if only because they look to have the most experienced defense in the league.  So it should be a better year for the Pioneers in league, as they’ll have an outside chance at home ice.
  • Miami: Sorry, Redhawks. The underlying metrics just don’t add up for you. Miami returns almost all its personnel from last year, and so do most other teams. What makes you think this year is going to have different results? Miami has talent, and maybe last year was an off year, but that talent had 24 chances to prove itself in the NCHC and never did. I do anticipate Miami’s possession improving, given all that experience, but not enough to move the needle significantly. Miami won’t finish last, but they probably won’t get home ice, either.
  • Minnesota-Duluth: UMD will regain their crown as possession champs this year. Goaltending will be a question though, as two goalies who split time last year will return. I’ll give Duluth the benefit of the doubt and assume they go with the better glove, but even then, shooting % is a little low. Should be a good year for them, and they can likely attain home ice once again, but the points will be very close.
  • Nebraska-Omaha: Yes, UNO lost some high performers. Yes, there are 11 freshman. However, UNO’s seniors were actually dragging the shot percentage significantly down last year, while eating up puck time. And while last year’s freshmen were phenomenal, the incoming class may be the best in school history. The goaltending will probably again be sub-par, but assuming Ryan Massa sees most of the goal time, it might be slightly improved. Possession will almost assuredly tank – expect UNO to be no better than league average there. But overall, UNO’s numbers look pretty good.
  • North Dakota: What’s there to say here? High shooting percentage, best returning goaltending, and their possession numbers should improve given all the returning key players, and this team is young and talented. Not only should North Dakota win the league with points to spare, they’re yet again legit Frozen Four contenders. Team to beat – no questions asked. Even the data says so.
  • St. Cloud State: The Huskies lose too much sharpshooting and an excellent goaltender. The seniors’ metrics don’t look great, and your sophomores didn’t get much experience last year. Hopefully the incoming freshman perform better than last year’s. Expect shot and save percentage to be down, expect possession to remain underwater, and don’t expect to win the league this year, but odds for home ice are better than not.
  • Western Michigan: Two of the best Bronco shooters are gone, and two average goaltenders return. Possession was a struggle last year for WMU, so expect similar struggles this year, especially since last year’s top two defenders are gone, too. It’s not personal, Broncos. Your numbers don’t look that bad, it’s just that everyone else’s look so much better.

There you have it, a stats-based 2015 NCHC Prediction. All of these point predictions are plus/minus 4.85 points. Given that confidence interval, we’re almost certain UND won’t finish last, and we’re almost certain CC or Western Michigan won’t finish first. Every other spot is up for grabs.

Now, just to be clear, the inputs are up for debate until a puck is dropped. Here are the admitted weaknesses that could contribute to noise in the model:

  • Wild fluctuations from last year’s numbers: My estimated shot%, save% and possession are all based off last year’s performance, so the prediction might be over reliant on NCHC 2013-14. However, a majority of last year’s players are returning, and what evidence do we have at this point to assume their performance will be wildly different than last year? Possible major divergences? Yes. Likely? Less so.
  • The Quinnipiac effect: Teams can throw off the predictions and skew their numbers by beating up on weak teams, or with clutch performances in close games. Basically any inconsistent play will add noise.
  • Injuries/departures/playing time: If anything affects the general composition of a roster, the independent variables are going to change. Specifically, any goalie injuries are going to throw the inputs off quite a bit.
  • New coaching styles: I’ll be watching CC closely. New coaches could completely throw this whole thing.
  • Ties: I didn’t test this, but it looks like teams that get more ties diverge more from the predictions. Makes total sense – it means they’re playing closer games that introduce more chance into final results and final points.

We’ll have a better idea of final standings after 2-3 NCHC series this season, but I have yet to explore what the relationship between early performance and final performance looked like in 2013-14. That’s my next step, but that’s another article.

So, once again, here’s our 2015 NCHC prediction:

2015 NCHC Prediction

Team '15 Shot% '15 Save%  '15 Poss% '15 Points* '15 Finish
North Dakota 11.26%  92.03% 49.50% 48 1
Nebraska Omaha 10.82% 90.45% 49.50% 41 2
Minnesota Duluth 9.05% 89.35% 54.50% 36 3
St. Cloud State 10.02% 90.21% 49.00% 36 3
Denver 9.44% 91.45% 47.50% 36 3
Miami 7.81% 90.90% 52.75% 34 6
Western Michigan 8.68% 90.45% 48.50% 30 7
Colorado College 8.31% 89.72% 48.75% 27 8
ALL NCHC 9.43% 90.57% 50.00% 288
*All 14-15 expected points +-4.85

For now, bring on the haters. We won’t know until the end of the season whether we’re on to something or completely wrong. But one thing is for sure – even if I’m full of crap, I’m not any more of a bullshitter than the NCHC writers. After all, last year they picked Miami first, and UNO last. There’s nothing to say they’ll do any better in 2015, and if they’re wrong, I’m probably at least partially right.

So I’ve got that going for me.

Leave a Reply

Your email address will not be published. Required fields are marked *