THE BOOK cover
The Unwritten Book is Finally Written!
An in-depth analysis of: The sacrifice bunt, batter/pitcher matchups, the intentional base on balls, optimizing a batting lineup, hot and cold streaks, clutch performance, platooning strategies, and much more.
Read Excerpts & Customer Reviews

Buy The Book from Amazon


SABR101 required reading if you enter this site. Check out the Sabermetric Wiki. And interesting baseball books.
MOST RECENT ARTICLES
MAIL : You ask | We say

Advanced


THE BOOK--Playing The Percentages In Baseball

Filter posts by...

 

Tuesday, December 28, 2010

Mathematical sleight of hand

By Tangotiger, 03:00 PM

Steve Landsburg offers this very ambiguous question (and the answer is here).  Phil Birnbaum explains the answer Steve is looking for by using baseball (always a winner with me).

If you don’t want to read all that, suppose you have this:
1 boy, 0 girls = 0% girls
1 boy, 1 girl = 50% girls
1 boy, 2 girls = 67% girls

The total is obviously 3 boys and 3 girls, meaning 50% of the kids are girls.  But, if you take the simple average of 0%, 50% and 67%, you are obviously not going to get 50% girls as the average.

Landsburg however phrases his question that the obvious answer is no longer obvious, by asking this:

There’s a certain country where everybody wants to have a son. Therefore each couple keeps having children until they have a boy; then they stop. What fraction of the population is female?… But in expectation, what fraction of the population is female?

And then he adds:

In other words, if there were many such countries, what fraction would you expect to observe on average?

His “other words” in no way is “other words”.  It basically adds a totally new question to the question he originally has.  Furthermore, what he should have said is:

In other words, if there were many such countries, what fraction would you expect to observe on average from a random country?

Why for example is it presumed that you would poll each country equally?  I don’t know about you, but when I sample results, I’m going to weight results in USA more than in Canada.  If one country has 1 million boys and 1.5 million girls, and another country has one million boys and 0.5 million girls, why would I sample the two countries the same, see that one has 60% girls, the other has 33% girls and come away with an average of 47%?

By adding “from a random country”, he makes it clear that the sampling unit is countries, and not people.

Landsburg however defends himself presuming that his question was clear, honest and unambiguous.  It could have been a fantastic question, properly worded.  Instead, it’s a mathematical sleight of hand.

(64) Comments • 2011/01/04 • SabermetricsStatistical_Theory
Page 1 of 1 pages

Latest...

COMMENTS

May 26 03:03
Pete Palmer’s new book: Basic Ball

May 26 01:11
Largest demonstration in Canadian history?

May 25 23:40
“Why Kickstarter works”

May 25 19:41
What sabermetrics is NOT

May 25 16:59
Howard Stern

May 25 15:12
Do pitcher’s reach back for velocity when needed?

May 25 12:51
Chad Curtis

May 25 11:26
Lack of hustle during a game

May 25 10:58
Rooting for laundry

May 25 02:38
NFLPA lawsuit against collusion

THREADS

December 28, 2010
Mathematical sleight of hand