Baseball for the Thinking Fan

Login | Register | Feedback

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

Tuesday, March 24, 2020

Projection Hindsight Is 20/20 and It’s Totally Awesome

One of the things you have to get used to when you work with projections is being wrong. Like, All. Of. The. Time. While I’d like to believe that the projections are accurate and it’s just real life that mucked things up, that isn’t quite how they work. There are always events you didn’t see coming, assumptions you made erroneously, and just plain old irreducible error, all of which are going to thwart you.

On a basic level, you’re supposed to be wrong. Imagine a world in which you knew, for an exact fact, that every team was a coin flip to win every game. With this perfect knowledge, you’d still expect nearly a quarter of the league to win either 73 games or fewer, or 89 games or more, through nothing but luck. For the math-inclined, this is a hypergeometric distribution, not a binomial one; the coin flips are not independent because the win totals will still add up to 2,430 and one team’s win invariably is another team’s loss. Here’s a quick table for some of the win totals, showing the probability of a team winning exactly X games and how many of the teams you’d expect to have won up to X games:


As an example, you’d expect 3.4% of those coin flip teams to win exactly 74 games, with 15% of all teams winning up to 74 games.

But we don’t have anywhere near perfect knowledge about how good a team will be. We’re not even in the same zip code as “near perfect”; we just hope to be on the right continent. As a result, our error bars are going to be significantly larger than even the rather erroneous results you still get with omniscient projections.

One of the best courses I ever took in college was a one-off course concerning Predicting The Future- as a result, this sort of consideration is of deep interest to me.


QLE Posted: March 24, 2020 at 12:52 AM | 4 comment(s) Login to Bookmark
  Tags: dan szymborski, projections, where did we go wrong

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. The 15-Day DL Posted: March 24, 2020 at 08:27 AM (#5933011)
On the flip side, ZiPS overrated the Tigers, Padres, and Red Sox by an average of 14 wins in 2019, an error that is cut nearly in half once you know who actually took the field. I under-projected the plate appearances of Fernando Tatis Jr. and Luis Urías by about 40%, failed to anticipate players like Gordon Beckham getting so much playing time, and greatly overestimated the health of Boston’s non-Eduardo Rodriguez pitchers and Dustin Pedroia.
Son, nobody ever found success estimating any measure of health for Dustin Pedroia.
   2. Ron J Posted: March 24, 2020 at 08:59 AM (#5933026)
I knew it was a Szym article just based on the headline.

And Dan, you might want to consider looking at predicted runs scored and runs allowed with perfect information about playing time. This after all is really what you're predicting. There's noise in translating runs scored/allowed to wins and losses after all.

EDIT: Come to that, there's noise in converting counter stats into runs as well so it would be interesting to see where the noise is coming from.
   3. Swedish Chef Posted: March 24, 2020 at 09:58 AM (#5933059)
Son, nobody ever found success estimating any measure of health for Dustin Pedroia.

Ask your cousin the 60-Day DL
   4. Walt Davis Posted: March 24, 2020 at 06:12 PM (#5933196)
ZiPS is not a playing time projection system. :-)

You must be Registered and Logged In to post comments.



<< Back to main


All News | Prime News

Old-School Newsstand

BBTF Partner

Dynasty League Baseball

Support BBTF


Thanks to
for his generous support.


You must be logged in to view your Bookmarks.

Hot Topics

NewsblogUS-based pro sports leagues monitoring coronavirus outbreak
(3375 - 3:41am, Mar 30)
Last: the Centaur Nipple Paradox (CoB).

NewsblogBaseball Question of the Day: Who’d you think would be a star but wasn’t?
(122 - 1:18am, Mar 30)
Last: TR_Sullivan

NewsblogMLB final pitch could be closer to Christmas than Halloween
(5 - 10:47pm, Mar 29)
Last: Doug Jones threw harder than me

NewsblogDodgers snapshot: Nomomania grips L.A. and Japan when Hideo Nomo dominates in 1995
(9 - 10:41pm, Mar 29)
Last: Greg K

NewsblogMLBPA chief Tony Clark says 'no door is closed' for playing the 2020 All-Star Game after COVID-19 pa
(22 - 10:35pm, Mar 29)
Last: Misirlou cut his hair and moved to Rome

NewsblogWhite Sox 2005 Rewind: Scott Podsednik and the art of making things happen
(1 - 10:23pm, Mar 29)
Last: DJS Thinks Apples and Oranges are Similar

NewsblogOT - NBA Thread 2020
(1993 - 10:21pm, Mar 29)
Last: Howie Menckel

NewsblogEx-Astros slugger Jimmy Wynn, nicknamed 'Toy Cannon,' dies at 78
(44 - 8:23pm, Mar 29)
Last: DanG

NewsblogHow the Cleveland Indians’ Lineup Dynasty Was Assembled
(4 - 7:41pm, Mar 29)
Last: ajnrules

NewsblogReport: Mets Trying to 'Drum Up Interest' in Sale During Coronavirus Hiatus
(10 - 5:58pm, Mar 29)
Last: Howie Menckel

NewsblogReport: MLB to expand rosters once season starts
(8 - 4:29pm, Mar 29)
Last: wjones

NewsblogD-backs troll Giants over Madison Bumgarner signing, 2017 Opening Day
(1 - 4:09pm, Mar 29)
Last: bbmck

NewsblogBaseball Question of the Day: What’s the coolest thing you have ever seen at a ballpark?
(105 - 11:30am, Mar 29)
Last: pikepredator

NewsblogBaseball Question of the Day: What is your least-popular baseball opinion?
(142 - 9:42am, Mar 29)
Last: pikepredator

Hall of MeritMost Meritorious Player: 1925 Ballot
(4 - 9:41am, Mar 29)
Last: John (You Can Call Me Grandma) Murphy

Page rendered in 0.2506 seconds
46 querie(s) executed