Baseball for the Thinking Fan

Login | Register | Feedback

btf_logo
You are here > Home > Baseball Newsstand > Baseball Primer Newsblog > Discussion
Baseball Primer Newsblog
— The Best News Links from the Baseball Newsstand

Thursday, February 21, 2013

Fangraphs: Larson: Evaluating 2012 Projections

The results of the 2012 forecasting competition.  Composite projections came out the best, but Jared Cross’s Steamer finished first among the independently generated ones.

David Concepcion de la Desviacion Estandar (Dan R) Posted: February 21, 2013 at 04:25 PM | 6 comment(s) Login to Bookmark
  Tags: projections

Reader Comments and Retorts

Go to end of page

Statements posted here are those of our readers and do not represent the BaseballThinkFactory. Names are provided by the poster and are not verified. We ask that posters follow our submission policy. Please report any inappropriate comments.

   1. Danny Posted: February 21, 2013 at 07:35 PM (#4373663)
Yeah, this is a bit like comparing 538/Pollster/RCP to Gallup/PPP/Marist. The former aren't possible without the latter. And I cringed a bit where he said "My personal projections (Larson) took 2nd" given that his "personal projections" are just an averaging of other projections.

Dan, how do you use Pitch F/X in your projections? IIRC, Steamer's use of velocity was credited for its strong pitcher projections the past couple years. Do you use more than velocity?
   2. Walt Davis Posted: February 21, 2013 at 08:51 PM (#4373685)
I assume the target audience for this is traditional 5x5 fantasy players since the projection systems are evaluated using those categories. A title that makes that clear would have been a good idea. If this was meant as a serious evaluation of how well these projection systems predict performance, it's not well done because it's focusing on categories that don't matter much.

I look at two main bases of comparison: the first is the Root Mean Squared Error both with and without bias. Bias is important to consider because it is easily removed from a forecast and it can mask an otherwise good forecasting approach. For example, Marcel projections show very little bias, giving them a low RMSE, but are very poor at predicting variation among players, meaning that it’s not a terribly good forecast if you’re trying to rank expectations of future performance.

Eek! The only "bias" which should be removed is if the projection systems are projecting to different offensive environments (which they often are ... would be good if all the systems just adopted a standard, e.g. the previous year's averages). But if the bias is from other source then it's crucial to retain it in any evaluation. And a low bias method is only problematic for projection if it's lower bias was just random -- if Marcel is consistently lower bias, that's a huge advantage. (I suspect it's not and it is about the different contexts being projected to. Also the author seems to be suggesting that the variance in Marcel is so large that it outweighs the bias advantage -- i.e. it has a large RMSE anyway -- which would be a legit reason it would perform poorly.)

Also please stop averaging ranks as being a useful way to rate things. It assumes that each of the categories is equally important (which in 5x5 fantasy I suppose they are but not in any context that really matters) and that the difference between a rank of 4 vs. 5 (where the actual difference could be tiny) is the same as the difference between 1 and 2 (where the difference might be substantial). Add up the projections to get projected Rbat, Rbase, etc. and go from there.
   3. David Concepcion de la Desviacion Estandar (Dan R) Posted: February 22, 2013 at 02:26 PM (#4374145)
Danny, I made that same point in my comment--my forecasts are probably say 85% intelligent (rather than rote equal-weighted) averaging of other systems, and 15% extra goodies. I do use more than just velocity, yes. Shoot me an email if you're curious about the details.
   4. The kids disappeared, now Der-K has too much candy Posted: February 22, 2013 at 04:11 PM (#4374242)
Is this contest judging on a mix of rate and counting stats?
   5. DJS and the Infinite Sadness Posted: February 22, 2013 at 04:45 PM (#4374276)
Yeah, it's 4x4 fantasy evaluations. ZiPS always gets reamed in the ones with counting stats, as I make no attempt to tailor the playing time projections to my prediction of playing time.
   6. AROM Posted: February 22, 2013 at 04:57 PM (#4374291)
ZiPS always gets reamed in the ones with counting stats, as I make no attempt to tailor the playing time projections to my prediction of playing time.


Mine always did too, until I mixed my rate stats with Tango's wisdom of the crowds playing time estimates. I try to answer the question "Who should play" while not caring so much about "how much will he play".

That's worked out OK for me.

You must be Registered and Logged In to post comments.

 

 

<< Back to main

BBTF Partner

Support BBTF

donate

Thanks to
Edmundo got dem ol' Kozma blues again mama
for his generous support.

Bookmarks

You must be logged in to view your Bookmarks.

Hot Topics

NewsblogOT: Politics - December 2014: Baseball & Politics Collide in New Thriller
(5055 - 8:35pm, Dec 19)
Last: Ray (RDP)

NewsblogTrading Justin Upton means the Braves are in full rebuilding mode | Mark Bradley blog
(76 - 8:30pm, Dec 19)
Last: Rickey! trades in sheep and threats

NewsblogThe 2015 HOF Ballot Collecting Gizmo!
(112 - 8:20pm, Dec 19)
Last: Booey

NewsblogRoyals sign Kris Medlen to two-year deal - MLB Daily Dish
(32 - 8:20pm, Dec 19)
Last: WSPanic

NewsblogJerry Crasnick on Twitter: "Jake Peavy has agreed on 2 yr deal with
(11 - 8:16pm, Dec 19)
Last: Chipper Jonestown Massacre

NewsblogAmazin' Avenue - Cohen: Mets and Rockies discussing Troy Tulowitzki deal with Noah Syndergaard as the centerpiece
(31 - 7:56pm, Dec 19)
Last: Cargo Cultist

NewsblogPrimer Dugout (and link of the day) 12-19-2014
(10 - 7:47pm, Dec 19)
Last: bobm

NewsblogFull Count » Source: Red Sox close to deal sending Will Middlebrooks to Padres for Ryan Hanigan
(9 - 7:40pm, Dec 19)
Last: Steve Balboni's Personal Trainer

NewsblogOT: Monthly NBA Thread - December 2014
(739 - 7:02pm, Dec 19)
Last: Booey

NewsblogHow the Rays lost the City Council vote - DRaysBay
(4 - 6:55pm, Dec 19)
Last: RMc is a fine piece of cheese

NewsblogMax Scherzer not a realistic option, New York Yankees' Randy Levine says - ESPN New York
(66 - 6:47pm, Dec 19)
Last: bobm

NewsblogThe 4 surprisingly quiet teams of the MLB offseason
(26 - 6:43pm, Dec 19)
Last: bobm

NewsblogOT: NFL/NHL thread
(9173 - 5:25pm, Dec 19)
Last: Moses Taylor, Moses Taylor

NewsblogOT: Wrestling Thread November 2014
(159 - 5:04pm, Dec 19)
Last: NJ in DC (Now with Wife!)

Hall of MeritMost Meritorious Player: 1960 Ballot
(10 - 4:34pm, Dec 19)
Last: DL from MN

Page rendered in 0.2137 seconds
48 querie(s) executed