RAPM error metrics

[italia13calcio]

Doing some benchmarking of models. Wanted to validate results. Does anyone either know if error metrics associated with RAPM (r2, mse, rmse, etc) have been reported here or elsewhere, or does anyone have the time/setup to run on their own and confirm w me? Thnx

[Crow]

I recall hearing awkward to get right... but low... but not specified in writing.

I think Joe Sill reported RAPM errors in the 2s way back when. Most or all of his stuff is difficult to impossible to find online elsewhere. Maybe via search of this site? I might have something in deep files but don't have time to look right now. Search J.E. and see what he has said or tweet at him in addition to this request. Or Steve Ilardi.

[jsill]

There is some discussion of RMSE and R^2 (in terms of predicting game margins) in my Sloan paper, which is available on the conference website:

http://www.sloansportsconference.com/wp ... thLogo.pdf

[Crow]

Thanks for replying.

[italia13calcio]

Thanks for the reply. However, I am looking more for error metrics on possession basis, as opposed to on a game basis (which seems to be all that is reported in the paper, although perhaps I am missing something...)

Thanks for pointing me in the right direction tho