Saturday, April 12, 2008

Mean, Median and Sex

I found the workings of an old post I never got around to posting. So here it is.

Time for a maths lesson for Gina Kolata of the New York Times, who reported on a survey that found:

…men had a median of seven female sex partners. Women had a median of four male sex partners. Another study, by British researchers, stated that men had 12.7 heterosexual partners in their lifetimes and women had 6.5.

Apparently "mathematicians" don't understand the difference between various measures of central tendency:

But there is just one problem, mathematicians say. It is logically impossible for heterosexual men to have more partners on average than heterosexual women. Those survey results cannot be correct.

Um, yeah, they can. This falls under the category of Misuse of Information. The explanation is pretty much the same as the example in our book, but dirtier.

The mean number of partners for men and woman has to be the same. But the median, as was quoted above, does not. The majority of women tend to have less sexual partners than the majority of men. The median for women is lower. However, there could be enough dirty women who have many, many partners - enough to keep the means even, but skew the distribution.

To be fair to Kolata, she and her mathematician corrected this the next week:

He had looked at the actual data from the survey citing medians and found that it could not possibly be correct. Of course he knew the difference between a median and a mean.

It's still a good example nonetheless. (And a good example of why you should always say what you mean, with all the caveats, as clearly as possible.)