Quote:
Originally Posted by New Era
I've pointed this out in numerous advanced stats threads but was told the problem does not exist, even though it is a well known problem in hockey circles. I was attacked by the hardcore believers for pointing out the glaring weakness in the methodology. Be prepared for the same.
|
God, you're dramatic.
It was pointed out to you that while there is indeed a problem in the accuracy of shot counts from one building to the next, it is somewhat negligible when it comes to the results that are produced from large samples of data. There is plenty of information about this available by way of a simple google search.
For example:
Quote:
Applying our methodology to data from six regular seasons (2007-08 through 2012-13), we find that for the most part NHL rinks (and the individuals therein) do a reasonably consistent job of recording events. This is especially true of the recording of SHOTs, which has the fewest rinks with significant recording issues and has the smallest rink effects that we found...
While event counts are impacted by rink effect, ratios of events such as Corsi For Percentage remain relatively unaffected.
|
And I seriously doubt that anyone "attacked" you for pointing to this "glaring weakness." Given your own abrasive posting style, the responses that I have seen to your critical arguments against the validity of so-called advanced statistics by what I would consider rather level-headed proponents have been par for the course. This case is no different.
While I am not convinced about the effectiveness of CORSI, Rel. CORSI, Fenwick as measurements for predicting future outcomes, they DO remain useful statistics when applied in combination with other data.