SIERA Mailbag
Please leave questions about SIERA in the comments to this post. I will respond to as many as possible in a follow-up post soon. Thank you all for your interest.
Matt writes for FanGraphs and The Hardball Times, and models arbitration salaries for MLB Trade Rumors. Follow him on Twitter @Matt_Swa.
Will SIERA get me laid?
We’re All Gonna Go Dateless
I having trouble with Kings Quest V can you tell me how to get started when I’m on the island with the moat?
You’re screwed…Kings Quest I was hard enough. I can’t imagine V being easier.
I can, however, help you get through Space Quests I – IV (though I’m a bit hazy on II), Quest for Glory/Hero’s Quest I and Gold Rush.
LMAO.
Can you give some of the details to the analysis showing that, stripping out the effects of fly balls, high strikeout pitchers have lower BABIP?
I’m interested in this too. Also, vice-versa.
How much of a low BABIP is caused by each variable?
How do you convert from SIERA into SIRA (turn it into runs, rather than earned runs)? Do you just have to estimate, or is there a change you can make in the formula? Thanks!
Can you type out exactly how the formula should look. I know you posted the coefficients but I cannot find an actual copy of the new formula spelled out in any of the articles.
Thanks!
Well, the mailbag probably seemed like a good idea at the time. *Grin*
LOL at the Kings Quest question. Anyone else remember the hotline numbers you had to call to get answers for such questions for Kings Quest, Police Quest, etc?
Anyway, I did want to voice some appreciation for SIERA and the process. I’m thankful that people are taking a look at individual pitchers and pitcher types in regards to influencing BABIP and things of that nature. I find it very frustrating that the “.300 BABIP” is just assumed to be a given for every pitcher.
We all know from playing experience and observations that certain guys are just harder to hit than others. We know this from strikeouts, weak contact, etc … even at the major league level where the difference will be reduced (as say compared to college and high school).
Could the correlation between high strikeouts and lower babip be that high strikeout pitchers have men on base at a lower percent (overall, not babip) than a pitcher in all ways similar but with a lower strikeout rate? Since the defense shifts to a different alignment when a man is on first that allows them to hold runners on and turn double plays it would make sense that the defense wouldn’t get to the same number of balls in play when runners are on.
Great thought. Better positioning could be a factor.
Probably a silly question, but:
Why do we want to predict future ERA? If we’ve decided that ERA is a “bad” metric for evaluating pitchers, why are we anchoring against it?
I understand the fantasy applications, but if we’re trying to get a handle on how good a play is – shouldn’t we consider a better measure of player value?
Your SIERA is your SIERA and your xFIP is your xFIP. I believe the only reason the formulas are made to produce a similar output to ERA is for familiarity against a stat used by the masses.
You have to remember why we’re using stats like SIERA in the first place. The goal of pitching is to get outs and avoid giving up runs. ERA tells us the rate at which runs were scored against the pitcher, which can be useful. The problem isn’t ERA itself, it’s how ERA is applied, namely as a determiner of skill when there are other huge factors that are out of a pitcher’s control that ERA blames or credits the pitcher for. Our goal is to try to measure a pitcher’s skill, but the reason for that is to be able to predict how many runs that pitcher will give up, which is ultimately what matters in games. We may not be able to predict the other factors that influence ERA, but we can at least see who the most skilled pitcher is, and the more skilled pitcher should give up fewer runs than the less skilled pitcher.
What happens to the suggested appearance of multicollinearity in SIERA when you apply Principal Components?
Baseball Prospectus recently put up an article essentially questioning the merits of SIERA. Have you read the article, and if so how would you respond to their criticisms (IE the unnecessary complexity and risk for confounding variables?)
He replied to a bunch of Colin’s criticisms over at Tango’s blog over the weekend.
Matt, Great work, as always. Been a huge fan since BP Idol and your work on SIERA and home field advantage. My question: Regarding the extreme similarity of SIRA vs SIERA rankings, can’t I just gross up SIERA by 9% (very close to the consistent MLB ratio of total runs over earned runs)?
Follow-up question: You have posted comparisons of next year predictiveness (?) for SIERA vs. xFIP, FIP, QERA (which as I recall from your initial research was very weak). How does it do vs. PECOTA ERA predictions? Are those simply QERA adjusted for body type and age?
Since the correlation of your version of SIERA to xFIP is .94, is it really worth all the complications and the annual tweaking to add an unproven statistic?
Did you do a Box-Cox test or something similar on the relationship between the independent variables and ERA? Basically how did you determine a linear model was appropriate?
I’d also like to echo the above comment that asks why we are trying to predict ERA when ERA is flawed. I guess there’s nothing obviously better to regress against?
How do you explain pitchers whose ERAs consistently beat their SIERAs year to year (such as Mark Buehrle)? Are they just recipients of very good luck or do they have some skill that SIERA is not accounting for?
Why hasn’t SIERA appeared on Dashboard of League Leaders?
Under the “Advanced” tab.
Why did Baseball Prospectus fire you?
Matt, do you have any idea why Colin, outside of his (what I believe to be) valid criticisms, has a complete inability to consistently communicate in a professional manner?
Never mind, I realize you have too much tact to respond to that. This debate has been intellectually interesting, but the tone has been occasionally unfortunate.
What is SIERA? Sounds like xFIP to me. Give me one sentence on it. I think you already covered this in a post but I’m a lazy asshole.
Will it be used in WAR instead of FIP any time soon?
Trying to post something, but my computer is having issues…
After reading through the SIERA articles and given the following gems over @ The Book:
“pre_introducing_batted_ball_fip_part_2”
“the_hr_per_fb_skill”
I can’t believe the number of people in the “community” who are not sure if pitchers have impact on HR/FB – even at large sample sizes.
What is Michael Cuddyer’s SIERA?
Which pitchers have the biggest difference between their xFIP and SIERA, and why?
Does SIERA adequately explain Worley’s season to date?
Considering TangoTiger’s work in the articles Matthew Cornwell points out above (a bit snarkily, however) and the incredible case of Matthew Cain (as well as the Giants as a team), is the next version of SIERA going to roll out soon with HR/FB data appropriately regressed?
Wasn’t trying to be snarky… just legitimately surprised. Sorry if it sounded like that. Look at Tom Glavine or Pedro’s career HR/FB vs. average. Glavine’s was even more drastic for a lot longer. Everybody acts like Matt Cain is the first guy with this ability. Tom Tango showed a pretty significant 1.38 z-score for pitchers in this area, when 1.00 would be found if HR/FB was all luck. In fact, Pizza Cutter and others have found similar if not slightly earlier r=.5 regression point for HR/FB compared to BABIP- which now, few have problems accepting pitchers have at least a little control over.
My comments were in response to a poster who said (paraphrasing) that we should ignore HR/FB data, because there are only 2-3 pitchers like Cain and that we have no idea how he is doing it.
Not only is the first point not true, but there are several factors that we know reduce HR/FB, such as pitch location Ex. Balls that are hit the other way are far less likely to become HR’s than balls that are pulled, so pitchers who get more opposite field contact give up fewer HR/FB. Not surprising, Tom Glavine had one of the largest opposite field vs. pull splits in history.