Printer-friendly

September 27, 2006

Lies, Damned Lies

Playoff Hurlers

by Nate Silver

While it's evident that there is nothing like a Diamondbacks-style Randy Johnson-Curt Schilling thunder-and-lightning duo among this year’s potential playoff teams, it’s unclear just which starting staff is the best of a relatively weak lot. The Twins, with Johan Santana & the Nobodies? The A’s, with Rich Harden joining Barry Zito and Dan Haren? The Tigers, who lead the majors in run prevention?

The best way to answer the question would be to run PECOTAs for all the pitchers involved, which would help us to separate skill from luck--Chien-Ming Wang has a better ERA and a better VORP on the season than Jake Peavy, but only those folks immediately east of the Hudson River would rather have Wang start a playoff game. However, PECOTAs are time-consuming to generate, so in their absence we’ll use a favorite toy of mine. I call this toy QuikERA (QERA), which estimates what a pitcher's ERA should be based solely on his strikeout rate, walk rate, and GB/FB ratio. These three components--K rate, BB rate, GB/FB--stabilize very quickly, and they have the strongest predictive relationship with a pitcher’s ERA going forward. What’s more, they are not very dependent on park effects, allowing us to make reasonable comparisons of pitchers across different teams.

The formula for QERA is as follows:

QERA =(2.69+K%*(-3.4)+BB%*3.88+GB%*(-0.66))^2

Note that everything ends up expressed in terms of percentages: strikeouts per opponent plate appearance, walks per opponent plate appearance, and groundballs as a percentage of all balls hit into play. Andy Pettitte, for example, has a 19.6% K rate, a 7.9% BB rate, and a 62.7% GB rate, giving him a QERA of 3.68. Note further that QERA is exponential, which is appropriate since run scoring is not linear. The QERA numbers used in this article are based on 2006 major league performance only.

We also need to have a way to account for the fact that the extra off-days in the postseason schedule allow a team to weight its outings toward its best starters. I looked at the distribution of playoff starts for all teams since 1995 that reached the World Series. It turns out that the average distribution is as follows: