from Amazon
Tuesday, February 15, 2011
Forecasts: Humans v Mechanical
Will Larson looks at hitters and pitchers:
http://www.fangraphs.com/community/index.php/comparing-2010-hitter-forecasts-part-1-which-system-is-the-best/
http://www.fangraphs.com/community/index.php/comparing-2010-pitcher-forecasts/
Colin notes in the comments:
So when you figure the average bias, do you prorate based on playing time?
And Will responded: Nope! Which, frankly, is ridiculous. The bias corrector MUST be applied on a per PA or per AB basis. (This “bias” is really “how much over or below the population actual was the population forecasted?”.) None of us stand behind the playing time forecasts, so, you simply can’t do what he did.
Indeed, his tests mix and match rate stats and playing time stats which is confusing.
Clearly Will is pretty dedicated to do this. I would hope he improves his process. Let’s help him out.
He also has a website, which seems to collect forecasts. Looks like we have someone who is pretty dedicated here. If he’s open to straightening out some of his processes, maybe we have someone to do all our dirty work.
Recent comments
Older comments
Page 1 of 344 pages 1 2 3 > Last »Complete Archive – By Category
Complete Archive – By Date