2015-16

[Jim Hyla]

Notably, there is a general downward trend.  

Full history.

IMHO, this is a far more important stat.

Yup, if you score more of the goals than your opponents, you're more likely to have the better record.

[Trotsky]

Notably, there is a general downward trend.  

Full history.

IMHO, this is a far more important stat.

Yup, if you score more of the goals than your opponents, you're more likely to have the better record.

It also brings home just how traumatic 1993 was.  I saw 20 games that year.  Why couldn't I see 20 games ten years later?

[Tom Lento]

bemoan the fact that 2003 was really the only consistently effective team offense in the Schafer era (disclaimer - I don't know if that's actually true, but I suspect it was - 2005-06 and 2009-10 both had sub-3 GFAs despite some good scorers at the top of the lineup).

2005-06 yes (2.83), but 2009-10 was 3.15. 2004-2005 was 3.20.  Cornell is currently scoring way too few goals per game to even come close to competing at a nationally competitive level.

Right, sorry, estimation fail.

[Tom Lento]

2002-2015 scoring offense, cornell vs. d-1 average

Thanks very much for doing this, pfibiger. That's the exact data I've craved this week, but didn't have the time/patience to find myself.

Seconded. Also, I'm updating my hypothesis: either the rule changes haven't impacted (mean) scoring, or else (mean) scoring in college hockey was really headed into the shitter.

pfibiger - I wouldn't mind seeing the raw data. I don't know if I'll get to it but I might try to visualize balance between offense and defense against season outcomes.

[pfibiger]

Absolutely. Here's the spreadsheet:

https://dl.dropboxusercontent.com/u/233950/scoring%20offense%20year-by-year.xlsx

[billhoward]

And you were a gentleman to not start the plot at 2005, else Cornell's regression line would be steeper still.

Fascinating use of kinda-big data.

[Roy 82]

.... it seems like the rules will continue to favor offensive play going forward.

I agree. It is extremely difficult to score while skating backwards.:-D

[Towerroad]

Absolutely. Here's the spreadsheet:

https://dl.dropboxusercontent.com/u/233950/scoring%20offense%20year-by-year.xlsx

Thanks, The R squared does not tell the whole story. The t stats on the regression coefficients are significantly different at well beyond the 99% level. There is a significant diffference between Cornell's scoring trend and D1 College Hockey as a whole.

Correlation is not causation. The cause is still open to discussion, the difference is not.

[Dafatone]

Absolutely. Here's the spreadsheet:

https://dl.dropboxusercontent.com/u/233950/scoring%20offense%20year-by-year.xlsx

Thanks, The R squared does not tell the whole story. The t stats on the regression coefficients are significantly different at well beyond the 99% level. There is a significant diffference between Cornell's scoring trend and D1 College Hockey as a whole.

Correlation is not causation. The cause is still open to discussion, the difference is not.

It looks like (which is TOTALLY a scientific term) we'd be right around the national trend if we dropped this most recent season.  I mean, we'd also be right around there if we dropped a peak from a decade ago, and "just throw out this outlier" is an easy way to ruin stats, but to the extent that we tried and failed to do something different this year that could in theory be reversed, the drop in scoring across D1 makes our own drop at least look not as precipitous, although still pretty precipitous.

[Towerroad]

Absolutely. Here's the spreadsheet:

https://dl.dropboxusercontent.com/u/233950/scoring%20offense%20year-by-year.xlsx

Thanks, The R squared does not tell the whole story. The t stats on the regression coefficients are significantly different at well beyond the 99% level. There is a significant diffference between Cornell's scoring trend and D1 College Hockey as a whole.

Correlation is not causation. The cause is still open to discussion, the difference is not.

It looks like (which is TOTALLY a scientific term) we'd be right around the national trend if we dropped this most recent season.  I mean, we'd also be right around there if we dropped a peak from a decade ago, and "just throw out this outlier" is an easy way to ruin stats, but to the extent that we tried and failed to do something different this year that could in theory be reversed, the drop in scoring across D1 makes our own drop at least look not as precipitous, although still pretty precipitous.

Dropping this year does impact Cornells Coefficient. It improves from -0.086 to -0.071 (ie each year on average we averaged 0.086 goals per game less than the previous year) but the D1 trend is only -0.023. There is still a significant difference. Either way our rate of decline is 3X worse than the national trend.

This year may have been an abberation but going back to the "old way" has a solid history and it is not encouraging.

Projections are a tricky business but we could be in real trouble in 20 years or so.

[Trotsky]

Projections are a tricky business but we could be in real trouble in 20 years or so.

When we're scoring -2.5 goals per game?  ;-)

[Towerroad]

Projections are a tricky business but we could be in real trouble in 20 years or so.

When we're scoring -2.5 goals per game?  ;-)

If you believe the trend will persist, then in 20 years we would be scoring 1.4 to 1.8 fewer goals per game than we are now. In effect there would be no reason to even find guys that can skate, just 400 lb man mountains that can adsorb shot after shot. Gang them up in front of the goal and let the other side tire itself out shooting. Perhaps a random rebound would find it's way into the oppositions net since the other side would have no need for a sieve.

Like I said, projections can be tricky.

[Tom Lento]

Absolutely. Here's the spreadsheet:

https://dl.dropboxusercontent.com/u/233950/scoring%20offense%20year-by-year.xlsx

Thanks, The R squared does not tell the whole story. The t stats on the regression coefficients are significantly different at well beyond the 99% level. There is a significant diffference between Cornell's scoring trend and D1 College Hockey as a whole.

Correlation is not causation. The cause is still open to discussion, the difference is not.

What? You can't make an assertion like that on 10 high variance data points for a team average metric compared with 10 data points representing a national average. For one thing, this is totally un-normalized. Cornell's numbers are, well, Cornell's numbers against Cornell's record. The league average is the global average across all teams. It is NOT the expected goal scoring for a league average team against Cornell's schedule, which is more or less what you'd need to draw meaningful conclusions about Cornell's offensive execution during that time span.

The best you can discern from this is Cornell's overall pattern is to be somewhere around a league average offense. That's it. Really.

Also, everyone keeps talking about 2015 dragging the slope down as an outlier year, but nobody has yet pointed out that 2003 does the same. These numbers are very noisy, and comparing slopes of raw averages over time is not going to help you understand much about what's going on or, at this data volume, even if anything meaningful is going on.

[pfibiger]

So here's the same graph, comparing Cornell to ECAC average scoring. So we're closer to comparing scoring performance against common opponents. It was fascinating to watch ECAC teams pingpong from the top to the bottom of the list. Other than a run of 5 or so years where Yale was always at the top, one year Dartmouth would be #4 in the country, the next year they were #55. Pretty much everyone other than Cornell bounced around a bunch. While which team was at the top or bottom changed, that's a pretty flat line.

[Towerroad]

Absolutely. Here's the spreadsheet:

https://dl.dropboxusercontent.com/u/233950/scoring%20offense%20year-by-year.xlsx

Thanks, The R squared does not tell the whole story. The t stats on the regression coefficients are significantly different at well beyond the 99% level. There is a significant diffference between Cornell's scoring trend and D1 College Hockey as a whole.

Correlation is not causation. The cause is still open to discussion, the difference is not.

What? You can't make an assertion like that on 10 high variance data points for a team average metric compared with 10 data points representing a national average. For one thing, this is totally un-normalized. Cornell's numbers are, well, Cornell's numbers against Cornell's record. The league average is the global average across all teams. It is NOT the expected goal scoring for a league average team against Cornell's schedule, which is more or less what you'd need to draw meaningful conclusions about Cornell's offensive execution during that time span.

The best you can discern from this is Cornell's overall pattern is to be somewhere around a league average offense. That's it. Really.

Also, everyone keeps talking about 2015 dragging the slope down as an outlier year, but nobody has yet pointed out that 2003 does the same. These numbers are very noisy, and comparing slopes of raw averages over time is not going to help you understand much about what's going on or, at this data volume, even if anything meaningful is going on.

Sorry, but you can make those inferences at least on a statistical basis.

First of all, there are 14 data points for each series. I would like more data, who would not, but the stats work at some basic level.

Secondly, both coefficients are meaningfully differenct from the null hypothesis of 0 and differ from each other by meaningfull amounts.

As for differing variance. Yes they differ and they should but neither data set demonstrates heteroskedasity so there is no bias in the standard error of estimate.

You can make too much of this sort of analysis but you can't dismiss it. Our trend over the period is significantly different from the D1 average trend.