Adjusting Regression Means

Strikeouts are up, walks are down and we’d changed by not changing at all.

As Tango recently pointed out, Steamer was looking a a little pessimistic this year. Really, we were just a little behind the times. The good thing about basing our regression levels on pitch data is that if pitchers start throwing harder (and they have), Steamer adjusts accordingly. The bad news is that if they throw harder AND they strikeout even more batters than would be expected by this increase (they’ve done this too) we have a somewhat more complicated adjustment to make.


Our projections now attempt to take into account the league wide changes in strikeout and walk rates. The big thing you’ll notice is that ERA projections are down a bit. We’ve also added an adjustment based on the research done by Bill Petti and Jeff Zimmerman who found, among other things, that relievers’ strikeout rates drop off more steeply with age than starters’ strikeout rates do.

8 days till baseball… one major update to come.

7 thoughts on “Adjusting Regression Means”

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>