A year or so ago I heard about a couple of papers by Satoshi Kanazawa on "Engineers have more sons, nurses have more daughters" and "Beautiful parents have more daughters." The titles surprised me, because in my acquaintance with such data, I’d seen very little evidence of sex ratios at birth varying much at all, certainly not by 26% as was claimed in one of these papers. I looked into it and indeed it turned out that the findings could be explained as statistical artifacts–the key errors were, in one of the studies,
Andrew,Great post and fascinating story. It seems to me this may be an example of empiricism running up against cultural myth wish fulfillment. It may make people feel there's something more just and feel-good about a world where engineers are more likely to have sons and beautiful people and nurses are more likely to have daughters (for example, an engineering family could be perceived as more value-added for a son, a nursing family could be perceived as less value-added for a son, and a beautiful family could be perceived as more value-added for a daughter). I don't necessarily have the answers for what you should do, except to say that I think this is a rather common problem, particularly in fields that have been called the "softer sciences". I think I lot of popular claims in the social sciences in particular deserve rigorous scrutiny by statisticians, experimental psychologists, and others.
Robin,
Thanks for the link. I'd just assumed that the facial symmetry thing had been proved--it seemed so naturally true!
Hopefully Anonymous,Thanks for the link.... I cannot believe this article is going to be published.
I posted in January on a similar example, where people were too quick to believe that facial symmetry indicates beauty.
This article is awful.
http://www.psychologytoday....
Andrew,Great post and fascinating story. It seems to me this may be an example of empiricism running up against cultural myth wish fulfillment. It may make people feel there's something more just and feel-good about a world where engineers are more likely to have sons and beautiful people and nurses are more likely to have daughters (for example, an engineering family could be perceived as more value-added for a son, a nursing family could be perceived as less value-added for a son, and a beautiful family could be perceived as more value-added for a daughter). I don't necessarily have the answers for what you should do, except to say that I think this is a rather common problem, particularly in fields that have been called the "softer sciences". I think I lot of popular claims in the social sciences in particular deserve rigorous scrutiny by statisticians, experimental psychologists, and others.