[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
THE BOOK cover
The Unwritten Book
is Finally Written!

Read Excerpts & Reviews
E-Book available
as Amazon Kindle or
at iTunes for $9.99.

Hardcopy available at Amazon
SABR101 required reading if you enter this site. Check out the Sabermetric Wiki. And interesting baseball books.
Shop Amazon & Support This Blog
RECENT FORUM TOPICS
Jul 12 15:22 Marcels
Apr 16 14:31 Pitch Count Estimators
Mar 12 16:30 Appendix to THE BOOK - THE GORY DETAILS
Jan 29 09:41 NFL Overtime Idea
Jan 22 14:48 Weighting Years for NFL Player Projections
Jan 21 09:18 positional runs in pythagenpat
Oct 20 15:57 DRS: FG vs. BB-Ref

Advanced

Tangotiger Blog

A blog about baseball, hockey, life, and whatever else there is.

Thursday, April 09, 2015

Expectation from a random drawing

?Say you have a uniform distribution, like rolling a single dice (*).  Whether you throw a 2 or 3 or 6, all are equally likely.  The AVERAGE throw will be 3.5.  If you happen to throw a 6, was that "2.5" more than expected?  Is throwing a 4 only 0.5 more than expected?  Or, was 6 simply as expected as anything else, and you wouldn't describe it as anything other than that, and you certainly wouldn't try to differentiate throwing a 6 from throwing a 4?

(*) Die is a stupid word.  It's a dice.

Now, instead of a uniform distribution, you have a binomial distribution of observations for a single entity.  And you randomly draw from that distribution.  Again, would you say that randomly drawing a number from the tail is "higher" than expected than drawing from near the midpoint?  Or, is it simply comparing one random draw to another random draw?  That we don't need to "compare" each of the drawn samples to the midpoint.  It's all random anyway, so, we're bound to have one sample further away from the middle than another sample.  None of that tells us anything, once we've established it's random.

So, suppose that the league BABIP is .300, and there is no such thing as a talent at BABIP.  If we observe one pitcher at .340 and another at .270, do we need to say that one is +.040 and another is -.030?  Or, can we say that compared to the DISTRIBUTION of all possible values, .340 was just one random sample, and .270 is another random sample of the same distribution.  And so, since both are part of the same distribution, we don't need to worry about representing them as anything other than a random variation of the same talent.  And so, once you account for the fact that the .340 must have benefited from bad luck and the .270 pitcher benefited from good luck, they are both exactly the same thing.  

Basically, it doesn't make sense to compare an observation to the average, without accounting for the random variation.

(26) Comments • 2017/03/14 • Statistical_Theory

Latest...

COMMENTS

Nov 23 14:15
Layered wOBAcon

Nov 22 22:15
Cy Young Predictor 2024

Oct 28 17:25
Layered Hit Probability breakdown

Oct 15 13:42
Binomial fun: Best-of-3-all-home is equivalent to traditional Best-of-X where X is

Oct 14 14:31
NaiveWAR and VictoryShares

Oct 02 21:23
Component Run Values: TTO and BIP

Oct 02 11:06
FRV v DRS

Sep 28 22:34
Runs Above Average

Sep 16 16:46
Skenes v Webb: Illustrating Replacement Level in WAR

Sep 16 16:43
Sacrifice Steal Attempt

Sep 09 14:47
Can Wheeler win the Cy Young in 2024?

Sep 08 13:39
Small choices, big implications, in WAR

Sep 07 09:00
Why does Baseball Reference love Erick Fedde?

Sep 03 19:42
Re-Leveraging Aaron Judge

Aug 24 14:10
Science of baseball in 1957

THREADS

April 09, 2015
Expectation from a random drawing