Quote:
Originally Posted by Enoch Root
You mention two important points that corsi advocates continue to ignore...
- There are far too many outliers
- No one ever mentions the confidence intervals, because a) the sample sizes quoted are usually far too small to even have meaningful bands, and b) they don't understand them anyway.
Listen to your own language: 'it usually indicates teams that should do well'. Correct. With a relatively low correlation, and with far too many outliers, and with no discernible degrees of confidence, we can guesstimate that corsi will usually indicate teams that should do well. Super.
That is a far cry from determining Stanley Cup winners with a high degree of confidence, no? |
Well I don't agree that there are far too many outliers, but that's me. You're free to find fault if you require more data points, that's your prerogative. Even if there are outliers, they usually correct themselves by next season if the same pattern exists. You don't see teams that are continuously in the outlier area, so that suggests that over small sample sizes (and I would qualify an entire season as a small sample) that you can have teams that buck the trend.
I do agree that little attention is paid to the limited data points when correlating Corsi and winning percentage, and I definitely agree that nobody talks about confidence intervals, but that's because most guys doing it don't have a strong background in statistics, especially scientific statistics. It does indicate an opportunity for someone to create a gold standard of how to do the analysis effectively and what conclusions could be drawn from it.
But for now, it does help to understand what's going on with teams, and what fans could usually expect, which is actually pretty powerful in a league where getting 100 points in 82 games is considered a good season.
I could go on, but I think you get my point. They are reliable enough for most people in a sport where there is little predictive power in the stats since hockey is a continuous play sport with a LOT of chaotic events that defy rational analysis. It's difficult to do in hockey, period, but it's better than not having ANY analysis.