Delicious Dangles*
Guest
Because VAR (observed) is referring to the exact same thing as VAR (actual), and VAR (binomial variation is referring to the same thing as VAR (luck), the two formulas are identical!
Why are you able to assume that the variance due to luck is the same as your value for binomial variantion? If it is that simple, I question why others do calculations for this value, and get different results.
http://www.arcticicehockey.com/2010/11/22/1826590/luck-in-the-nhl-standings
http://blog.philbirnbaum.com/2013/01/luck-vs-talent-in-nhl-standings.html
http://www.bettingexpert.com/blog/football-luck
This has nothing to do with quantum mechanics. That is not what quantum mechanics suggests is random.Well - that sounds like a philosophical issue. Certainly, findings in fields like quantum mechanics would suggest that some things truly are random, and cannot be predicted.
Every action in hockey has a consistent reaction based on the applicable factors.
No, I do not have to do that. All I have to do is bring into question your statistics. Some things simply cannot be predicted with any worthwhile accuracy with our current wealth of knowledge and capabilities.In any event, when you develop your own model that's able to predict binomial variation, let me know. No excuses, right?
Assuming correct results, best possible methods, as a league average, based on 4 of over 100 years of data. So actually, you did, by applying those findings to an individual team.I made no such assumption.
The original inquiry was simply whether corsi and fenwick predict future results, when the original sample is smaller than 80 games, better than points percentage or goal differential. Which they do, as substantiated by the data I posted.
If corsi correlates to half of the teams perfectly and half of the teams horribly, you can get a correlation for the league that does not apply at all to half of the teams.
No you don't. You play the same teams the same amount of times in every year, assuming no rule changes. This is a large benefit for looking at full seasons. The roster changes from season to season tend to happen just as much as in-season roster changes.With an across season analysis, all those factors come into play as well, just like they do with a within season analysis.
Except with an across season analysis, you have the added effect of off-season roster acquisitions and departures.
So - quite clearly - a within season analysis has less confounding variables.
A larger sample also decreases the impact of your so-called luck, which you should want to do.
As I previously stated, this is not a requirement for questioning your method.Then devise your own method.