tag:blogger.com,1999:blog-12133335.post7524921903842392555..comments2016-02-06T10:53:17.484-05:00Comments on Walk Like a Sabermetrician: Crude Team Ratings, 2013phttp://www.blogger.com/profile/18057215403741682609noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-12133335.post-12193491936489588962014-01-14T22:08:52.891-05:002014-01-14T22:08:52.891-05:00I use the rule of thumb developed by Tango of addi...I use the rule of thumb developed by Tango of adding in 69 games of .500 performance. So regressed W% would be equal to (W + 34.5)/(W + L + 69). These ratings are based on win ratio, and I build the regression in to the win ratios that are inputted to develop the ratings rather than the ratings themselves, so the win ratio would be equal to (W + 34.5)/(L + 34.5).phttp://www.blogger.com/profile/18057215403741682609noreply@blogger.comtag:blogger.com,1999:blog-12133335.post-58246749159733723542014-01-14T17:38:02.495-05:002014-01-14T17:38:02.495-05:00Could you share how and by how much these figures ...Could you share how and by how much these figures would be regressed for estimates of win probabilities? How much would they be regressed 1/4 of the way through the season, 1/2, 3/4, during the playoffs, etc.?Anonymousnoreply@blogger.com