Charles Blow revisits familiar findings: “red” states have higher divorce rates as well as higher rates of teen pregnancy and higher rates of on-line pornography consumption. He writes:
bq. While conservatives fight to “defend” marriage from gays, they can’t keep theirs together. According to the Census Bureau’s Statistical Abstract, states that went Republican in November accounted for eight of the 10 states with the highest divorce rates in 2006.
Welcome to another episode of “The Ecological Fallacy“! Once again: you cannot infer the behavior of individuals — Democrats and Republicans — from data at an aggregate level, such as states.
What happens when we look at individual-level data? Blow’s story falls apart. Using the General Social Survey, I first created a relevant measure of marital status: whether the respondent was divorced or separated at the time of the interview, or had ever been divorced or separated. So you are coded 1 in those cases, and 0 otherwise (i.e., if you had never been married or if you were married or widowed but never divorced or separated). The GSS included marital status in 27 surveys between 1972-2008. These surveys contain about 50,000 respondents.
I also created a measure of whether the respondent admitted to having an affair (leaving aside the issue of how many survey respondents answer this question honestly). For this measure you are coded 1 if you admitted to having an extramarital affair and 0 if you had not. I excluded respondents who had never been married. So this measure includes only those who are married or were married at some point. The GSS included the affair question (charmingly labeled “evstray” in the dataset) in 10 surveys between 1991-2008. These surveys contain about 16,000 respondents.
What do we find? Simple descriptive statistics suggest only small differences between Democrats, Republicans, and independents (here, independents who “lean” toward a party are counted as partisans):
About 29% of Democrats, 30% of independents, and 26% of Republicans are or have been divorced or separated.
About 19% of Democrats, 19% of independents, and 15% of Republicans admit to having an extramarital affair.
If anything, Republicans are slightly _less_ likely than both Democrats and independents to get divorced or mess around. This is _the opposite_ of what Blow suggests — which, yet again, reveals the problems of using aggregate data to make individual-level inferences.
To see if additional factors could explain even these small differences among groups of partisans, I then estimated two logit models. Here, the probability of being divorced or having had an affair is a function of a binary measure of partisanship (coded 1 if Republican and 0 otherwise, since there appears to be little difference between Democrats and independents), as well as controls for these factors: age, sex, race, educational attainment, and year of survey.
There are statistically significant, but small, differences between Republicans and Democrats/independents: other things equal, Republicans are 2 percentage points less likely to be or have been divorced. They are 4 points less likely to admit to an extramarital affair. To put that latter effect in some context, men are about 9 points more likely than women to admit to an extramarital affair.
These effects are slightly larger if we focus only on the 2008 data: Republicans are 4 points less likely than Democrats or independents to be or have been divorced, and 5 points less likely to admit to an extramarital affair.
This is a very simple analysis. Perhaps there are other factors one should control for, and perhaps there are interactions between party identification and the partisanship of states — a la Andy et al.’s research.
But I think the basic finding is likely robust: partisanship has a very weak relationship with either divorce or infidelity, and the relationships that do exist suggest that Republicans are less, not more, likely to get divorced or be unfaithful. Those, like Blow, who want to decry Republican “hypocrisy” on issues of family and sexuality may want to focus their ire on Sanford, Ensign, et al., and not on Republicans in the mass public.