Nate Silver emphasizes that correlation is not causation, then offers an intriguing chart which suggests that states that banned gay marriage in the early part of the decade (mostly 2004) experienced an increase in their divorce rate in 2008.
Baffling. Nate takes a stab:
The differences are highly statistically significant. Nevertheless, they do not necessarily imply causation. The decision to ban same-sex marriage does not occur randomly throughout the states, but instead is strongly correlated with other factors, such as religiosity and political ideology, which we have made no attempt to account for. Nor do we know in which way the causal arrow might point. It could be that voters who have more marital problems of their own are more inclined to deny the right of marriage to same-sex couples.
Let me suggest a factor for which a statistical control would be appropriate - military families and military divorces. Per this article, the military divorce rate for was 3.6 percent for the year ending Sept 30 2009, compared to 2.6 percent in Sept 2001, prior to the deployments in Afghanistan and Iraq.
Those figures do not seem to include veterans and National Guardsmen. I am just guessing that the New England states whose courts led the charge on gay marriage are also under-represented in the population of military families. Conversely, plenty of Red states likely to have banned gay marriage also are likely to be overrepresented among to military bases, families, and divorces.
As to whether a 1% increase in the military divorce rate could drive a state's divorce rate from 1.90% to 2.04% (as was the case with Arizona), well, maybe - that is an increase of 0.14%, or 1/7 of the military rate. Could 1/7 of the Arizona married population have a military connection affected by the Iraq and Afghanistan deployments? That strikes me as high but not absurdly so.
Pew offers some statistics and thoughts for folks inclined to dig in, as does Nate.
MORE - RAISING ARIZONA: Per the CDC data provided by Nate we see that Arizona has roughly 24,000 divorces per year. An increase of 0.14% in the divorce rate is an increase of about 34 divorces [NO! The 0.14% should have been applied to the overall marriage rate - Divorces rose by roughly 1,650, per Taeyeong in the comments]. Per the earlier article, there were 27,312 military divorces nationwide in 2009. Since in 2001 the military divorce rate was 2.6%, let's say that (1 / 3.6) is the increase in divorces due to the two wars. That is roughly 9,000 additional military divorces nationwide. Could Arizona have picked up 34 of them? [Well, 34 is the wrong number and looked weirdly low, but if there were 1,650 divorces above baseline in Arizona alone and we have 9,000 military divorces above baseline to explain the national result, we are probably going to run out of military divorces. So add in divorces associated with deployed National Guardsmen and discharged vets, and where are we? I knew this looked too much like work...].
The orders of magnitude certainly suggest that military divorces would be a good place to look (they also suggest I ought to look for my calculator, but who has time?). Maybe the real answer is that two trends overlapped - a nationwide decline in the "civilian" divorce rate was offset by an increase in the military divorce rate. The net effect would be a rising rate in states with a higher proportion of military families and the gay marriage result would be a spurious correlation.
So who is going to check this out? Ride to the sound of guns!
WHO IS RELYING ON RIDICULOUS ARGUMENTS? Ezra Klein seems to have forgotten what side he is on and what he wrote. Not a bad strategy, actually, but let's enjoy the fun:
It's common to hear that gay marriage threatens traditional marriage. But Nate Silver runs the numbers and finds just the opposite. Since 2003, states that haven't banned gay marriage have seen an 8 percent drop in divorce rates. States that have passed gay-marriage bans, by contrast, have seen their divorce rates edge upwards. Does this prove causation? No. Does it prove that opponents of gay marriage rely on some ridiculous arguments? Yes.
Huh? Ezra admits that these numbers prove nothing, then uses them as evidence that the other side makes silly arguments? I'm twisting around like a defensive back covering Larry Fitzgerald.
As to the "marriage under assault" notion, let's turn the kiddies loose on this - here is a black minister from Boston discussing the Massachusetts gay marriage decision back in 2004:
Bishop Gilbert A. Thompson Sr., who as pastor of New Covenant Christian Church in Mattapan heads the largest Protestant congregation in Massachusetts, said black ministers have many reasons for speaking out against gay marriage.
"We're weighing in on this because we're concerned with the epidemic rate of fatherlessness in America and in our community, and we don't think gay marriage helps that cause," he said.
Maybe this minister thinks young black gangsta wanna-bes are less likely to get married if they perceive it as a "gay thing". Or maybe he is a bigoted homophobe. Ezra can make the call!
An earnestly liberal friend of mine once explained to me that he couldn't let his view on gay marriage be guided by the homophobia of some inner-city blacks. I wondered whether he was interested in foisting yet another grand liberal vision onto the black community and risk shattering black families as an unfortunate (yet predicted!) consequence and he glared at me, so it was a typical Saturday night.
MORE UNCRITICAL ACCEPTANCE: As evidence that when people see results they like their brains stop, I present Joe and the Maha. And the Prairie guy.
At the risk of "hijacking" this thread back to the original topic, the whole question of whether a state has or has not enacted a prohibition on gay marriage boils down to a single variable that Silver completely ignores: were the voters of State X given an opportunity to vote on a gay marriage ban? If they were, it passed handily. If they weren't, that says a lot more about the state of democracy in State X than it does about anyone's religion, political ideology, marital woes, gayness, or any of the other irrelevant factors Silver drones on about.
Posted by: Xrlq | January 15, 2010 at 11:30 PM