A recent analysis by Zach Goldberg addressed an issue I raised years ago: Why do liberal women report more sexual harassment? Goldberg found support for the view that liberal women are more sexual, and this invites unwanted attention. Research more generally finds that badly behaved females -- delinquents, drug users, prostitutes -- are targeted for sexual abuse.
Goldberg takes a bivariate approach. Let's do a multivariate analysis, so we can see if promiscuity explains the liberal-harassment link after adjusting for the influence of other factors. Using GSS data on almost 1,500 women, and employing binary logistic regression, we get a significant coefficient of .15; the more liberal you are, the greater your risk of being harassed.
Now let's see if it drops as we enter controls. Young people are more liberal and might be sexually targeted. If we add age to the model, the coefficient drops to .12. Age explains a little bit of the link.
How about education? Educated women are more liberal and might be more sensitive about unwanted attention. When we add years of education, the political orientation coefficient drops to .11. Not much change.
How about living in a large city? City dwellers are more liberal, and perhaps urban men are more aggressive. When we add size of the population, the liberalism slope increases to .12, so city size does not help explain the liberal-harassment association.
How about being single? Single women are more liberal and might draw more attention. When being single is added to the model, the politics coefficient drops back to .11, so marital status doesn't matter much.
Okay, how about number of sex partners in the past year? When added to the equation, the liberalism estimate only drops to .107. More sexual partners definitely predicts being harassed, but it does not appear to be the reason why liberal women are harassed more.
Since none of the examined variables explain much (age does a little), the answer seems to be something very close to political orientation. My guess is that social interactions are often ambiguous, and liberal women are inclined to interpret more interactions as sexually abusive. They've been indoctrinated to do so.
With all the vote counting shenanigans we see going on now, are liberals simply more dishonest people than conservatives? The short answer i...
In the comments in the last post , some readers contended that Jews are not ethnocentric. Using the same question I used in the comments se...
Via a reader at iSteve, it looks like this might be the vocabulary test used by the General Social Survey. (Someone please tell me if I'...
Which factor reduces family size the most? Below are the standardized OLS regression coefficients for a sample of whites ages 40-59: Stand...