-
studes Woohoo! I win!
Seriously, the main point is that none of these stats is all that good at predicting ERA, which is the conclusion I've come to in past columns.
Also, there is an error in the article. xFIP calculates home runs per outfield fly, not per fly.
-
Colin Wyers Retrosheet has four batted ball type codes - ground balls, line drives, fly balls and popups. I used all fly balls to calculate xFIP. Did I make a mistake somewhere?-
studes We use BIS data, not Retrosheet's.
-
-
-
Graham MacAree About what I expected. tRA is a little better than FIP but outperformed by xFIP, which sensibly incorporates regression.
I'll concede victory to Studes for now... but have you thought about doing a comparison using tRA*?
-
skyking162 Exactly. tRA (and FIP, and xFIP to a lesser extent) isn't necessarily built to project future performance, but instead indicate value of past performance, in a more context-neutral way. tRA* is to tRA what xFIP is to FIP, to some extent. So if we're projecting ERAs, tRA* is built better than tRA (probably) and should be included in this horse race as statcorner's main entry instead of tRA.-
studes Yup, which was the main point brought up in the THT Fantasy entry that started this whole thing. Really, Colin is reinforcing Derek's main point, that FIP and related stats aren't the best stats to use when predicting future ERA. They're intended to isolate pitching from fielding.
At THT, we like to use David Gassko's LIPS which, as far as I can tell, is pretty much the same thing as tRA*. And as Colin points out, you can use an updated projection for pitchers with enough major league experience.
-
skyking162 Good point. If predicting ERA, you bold to include park effects and defensive effects. An updated projection, using numbers like xFIP, tRA*, and LIPS and park/fielding adjustments would be the best route.
-
-
-
-
Derek Carty Colin, league average HR/OF is 11%-ish, not 13%. Although now I notice that you used Retrosheet data, so that might be why you used 13. Either way, interesting article. I still completely disagree, though, that ERA estimators have little use, at least for fantasy purposes. -
nickojohnson No QERA? I think it fits the stated requirements of being easy to calculate and publically available. I've always liked how it uses K% and BB% rather than rates/9 (although I know Derek you've argued against this in the past I think).
ERA, FIP, xFIP, tRA
THE BOOK--Playing The Percentages In Baseball —
Colin checks in to see how well they correlate.
Colin: if you have the r for that table, I’d love to see it.
Thursday's Short and Sweet Mug
Brew Crew Ball —
... Colin Weyers looks at FIP, xFIP, and tRA at THT. We've been discussing fielding independent metrics in regard to minor leaguers here lately, and it's a good summary if any of our readers are unfamiliar with each. It's telling that ERA does the poorest job of predicting future ERA. ...
xFIP versus FIP and a switch for RotoSavants
Roto Savants —
... Colin Wyers also at THT wrote on that today and found the root mean square error for each projection (including tRA). His findings showed that ERA was the worst predictor of future ERA as we would all assume, but xFIP and tRA are slightly better than FIP. He assumes we should stick to larger projection systems, but that is not in the context of fantasy sports. In fantasy baseball we have a different requirement for statistical analysis and can use these much differently. ...
THT:Colin Wyers: How well can we predict ERA?
BBTF's Baseball Primer Newsblog —
THT:Colin Wyers: How well can we predict ERA? Ability vs. Value I have written at length before on the basic principles of ability (or true-talent level) verus value. There’s just one point I want to come around and reemphasize. People tend to lean upon defense-independent estimates of pitching performance because they better predict future performance. (And, strictly speaking, they do.) This leads to a lot of fantastic confusion about the issue, with the argument being that if we want to look at past performance, we should ignore defense-independent measures and look at ...
Friday Morning Astros, etc. Round Up
The Crawfish Boxes —
... Colin Wyers, at The Hardball Times, probes whether component ERA's (FIP, xFIP, and tRA) are good predictors of future ERA. ...
The Scrap Heap
Another Cubs Blog —
... is good news.
Ozzie Guillen: Big-time Zambrano fan.
In the wake of the illegal leak of Sammy Sosa’s 2003 PED pop, Posnanski wonders if the HR has lost its signifcance. Also note how he has slickly gone from using “Steroid Era” to “Selig Era.” I think that’s a change I’m going to stick with. Selig deserves to have his name attached to this shit as much as any player.
Colin takes a closer look at the extent to which ERA can be predicted. ...
Fish Bites
Marlin Maniac | A Florida Marlins Blog —
... - For some generic news, check out Colin Wyers study on predictive power of defense-independent pitching stats. Of particular importance to people who aren’t sabermetrically-inclined: ERA does a very poor job of predicting ERA, so try to take a look at something better like FIP. Remember, pitchers can’t control how their fielders snag ground balls. ...
Daily Box Score 6/22: Called Shots, the Death of 3D Bill James, & The Bastardo Effect
Beyond the Box Score —
... to see which has the most predictive value. A regression analysis suggests xFIP just nudges out tRA. Correlation increased with IP, as would be expected. The problem with all these statistics (save ERA itself), Colin Wyers argues, is that they look only at components of a pitcher's success which are defensive-independent. However, ignoring defense does make component measures faulty predictors of future ERA, which is defense-dependent. A proper predictor, then, would have to include knowledge of team defense. Wyers suggests his own ...
Dan Wheeler's Life is Boring
DRaysBay —
... mso-para-margin-bottom:10.0pt;
mso-para-margin-left:0in;
line-height:115%;
mso-pagination:widow-orphan;
font-size:11.0pt;
font-family:"Calibri","sans-serif";
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:"Times New Roman";
mso-fareast-theme-font:minor-fareast;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;}
Colin Wyers ran a fantastic piece on predicting ERA a few days ago. Read it here. The basic summary: ...
Clippings from around baseball
True Blue LA —
R.J. Anderson | FanGraphs Baseball Game of the Week
BBTF's Transaction Oracle Discussion :: Yay Manny! Dan Symborski is rooting for Manny
Stacking the middle -- The Hardball Times Is the cliche "champion teams are strong up the middle" correct?
The WPA Inquirer -- The Hardball Times WPA revisited
How well can we predict ERA? -- The Hardball Times FIP or XERA or ???
Memories Of Kevin Malone: Jonathan Broxton Is A Robot Not a terminator bad guy but a terminator good ...
The 2009 NL Cy Young Award, and what are ERA+, VORP, xFIP, and tRA all about?
D'Backs' Venom —
... Why do analysts think this is more useful that looking at things like ERA? One, because it eliminates the huge variability of fielders from the equation. And two, because it turns out that using FIP is a better predictor of future performance than ERA (or ERA+). That is, a pitcher who has managed a low ERA despite high BB and HRs (hence a high FIP) is much more likely to see that ERA rise in the future than one with the same ERA and a low FIP. So it may be a better evaluator of a pitcher’s true performance and skill than ERA. ...
![Derek Jeter: Sportsman of the Year [Rumor Monger]](http://images.dailyradar.com/media/uploads/ballhype/story_preview/2009/11/27/derek_jeter_sportsman_of_the_year_rumor_monger.jpg){kind=small}
