I’ll be speaking on August 13 at the American Sociological Association meeting in Montreal. I’ll start with our red-state, blue-state analysis and then talk about some more recent work along these lines, including our anlaysis of Mexican voting data. Since it’s a methodological session, I’ll be focusing on some of the challenges we’ve faced in understanding and checking the varying-intercept, varying-slope multillevel models that we’ve been using. Any sociologists who are reading this: you have a couple of weeks to prepare some good questions…
Don't bother reading this one if you're not a sociologist.
Of course, your title ensures that we will all read this post, sociologists and non-sociologists alike.
Hi Andrew,
This comment is not related to the blog but I thought you might be interested. Did you come across the Freakonomics blog on "Why Do Beautiful Women Sometimes Marry Unattractive Men"? Here's the link to the blog: http://www.freakonomics.com/blog/2006/08/02/why-d…
Quoting from the blog … "Kanazawa argues it’s because good-looking parents are 36% more likely to have a baby daughter as their first child than a baby son—which suggests, evolutionarily speaking, that beauty is a trait more valuable for women than for men. The study was conducted with data from 3,000 Americans, derived from the National Longitudinal Study of Adolescent Health, and was published in the Journal of Theoretical Biology."
I was curious about what your thoughts on the subject were. :)
Neha,
I'm skeptical.
I read the Freakanomics blog entry. Dubner seems to be suggesting that Kanazawa could be fired (presumably for shoddy statistics?). That seems to be a bit extreme–after all, I published a false theorem myself once, and I don't think I should be fired! I do wonder about this line of research, though–I'd just assumed that the paper I'd noticed earlier was a one-shot deal. If it's a whole research program, perhaps it's worth looking at the numbers more carefully. After all, even if the article did make statistical errors, it's possible there's something there. I'm still skeptical (the coefficients just seem too huge; if there were effects, I'd expect to see things more on the order of 1% or 2%, which I think would be overwhelmed by selection problems with the data). But I'm certainly no expert in this area.