Flaws of Berri's Wins Produced Metric

Moderator: Doctor MJ

mysticbb
Banned User
Posts: 8,205
And1: 713
Joined: May 28, 2007
Contact:
   

Re: Flaws of Berri's Wins Produced Metric 

Post#21 » by mysticbb » Thu Feb 13, 2014 1:33 pm

Doctor MJ wrote:You'll note that the blog is not current, and this is common issue with such sites: The guys get hired by NBA teams, and they stop updating their site.


Indeed, countthebasket was the website made by Eli Witus, as I mentioned the current Vice President of Basketball Operations for the Houston Rockets.

Also, one of the best sites for raw data and so on was basketballvalue.com by Aaron Barzilai, currently the Director of Analytics for the 76ers, is gone for good. A year ago I had a conversation with him, in which he actually thought about keeping the site with the raw data updated, but I guess he hasn't the time for that anymore.

Doctor MJ wrote:And here's mysticbb's site, although I don't think it's really up-to-date right now. mystic though is about as sharp as they come in this:
http://bbmetrics.wordpress.com/


Thanks for the kind words, but as you said the blog is neither up-to-date nor does it contain many things about regression. SPM is purely a boxscore stat. Anyway, I can probably answer the most questions regarding regression analysis.

The underlying maths for OLS and Ridge Regression is in part explained here: http://www.apbr.org/metrics/viewtopic.p ... 239#p15811

I actually thought I did a better job than usual to explain it in a fashion easy to understand for others. But well, someone might disagree with that notion ... :)

Return to Statistical Analysis