There are lies, damned lies, and exit polls. A purported connection between race and homophobia has recently made the rounds, prompting big think pieces from the likes of the Washington Post. We’ve been told that 7 out of 10 African-Americans who went to the California polls voted yes on Proposition 8 — a measure that passed on Tuesday overruling the California Supreme Court judgment that legalized same-sex marriage.
Even more amazing than this is the way this correlation is getting a free pass. The only way you can bring a demographic into election statistics is through the exit poll. But exit polls have problems. Back in 2006, Mark Blumenthal initiated a helpful series of posts summarizing some of the flaws: where the interviewer is standing in relation to the polling place, how well-trained the interviewer is, the tendency for voters who volunteer to participate upon seeing the interviewer with the clipboard, the inclination for the polls to favor Democrats in presidential election since 1988, and so forth. In 2005, the Washington Post reported that interviewing for the 2004 exit polls was “the most inaccurate of any in the past five presidential elections.” Large numbers of Republicans refused to talk with interviewers, and this, in turn, led to an inflated estimate for John Kerry. But despite these problems, exit poll faith is a bit like stubborn fabric softener sticking to a hard wonk’s argyle sweater. In a longass Rolling Stone article, even Robert F. Kennedy, Jr. believed in the gospel, suggesting that exit polling was the first indicator that the 2004 election had been stolen. Political slickster Dick Morris went further, stating that “exit polls are almost never wrong.”
Edison Media Research and Mitofsky International were the team behind the 2004 polling botch, and this dynamic duo also spearheaded this week’s California exit polling. The hard data is not yet available at the Edison/Mitofsky site. But the Associated Press has reported that 2,240 California voters (of these, 765 were absentees interviewed by landline telephone), interviewed in 30 precincts, represented the total number of people that Edison/Mitofsky interviewed. Which means that some percentage of these voters were African-American. Let’s give Edison/Mitofsky 50%. That leaves us with a mere 1,120 voters.
A quick jaunt to the California Secretary of State’s website reveals that there are 25,423 precincts in California and that 10.5 million people turned out on Tuesday. In other words, Edison/Mitofsky is making a major claim based on 0.11% (a little more than one-tenth of 1%) of the total precincts, and a sample of voters smaller than a crab louse dancing in a thorny thatch of hair. Is this really large enough? Exit polls have proved somewhat accurate in relation to simple binary choices, but I’m wondering if it all turns to bunk when it comes to correlation. Perhaps a legion of statistics experts can help explain why Edison/Mitofsky can get away with this. Because I’m tempted to view this as a strange offshoot of the Bradley effect.
http://www.surveysystem.com/sscalc.htm
To get a confidence interval of +/-3% (a number I just pulled out of my hat), confidence level 95%, in a population of 10,000,000, you need a sample size of 1067 people. To get to 99%, you only need to get another 800 or so people.
You don’t actually need to poll a sizable fraction of the electorate to get an accurate poll. Hence why polls are even EVER used – if you had to poll 25% of the electorate, you might as well just have an entire election.
Polls are generally pretty lousy, so I always take them with a grain of salt. I find the idea of a connection in this case viable. The majority of African-Americans are church goers, and the bible thumpers were behind Prop 8. Then again, you could say the same about white people and Hispanics. There’s a connection, but they’re not the only group to blame. Every group seems to have a problem accepting gay marriage. Even our new president stands behind the whole “separate but equal” excuse (although that could be for political reasons).
People can’t legislate GLBT people out of existence, which seems to be the underlying goal. Someday the bigots will die out and there’ll be equality. How this inequality manages to be legal while we have the 1st amendment is beyond me.
As an African American heterosexual female, it really bothers me that a group’s constitutional right could be stripped from them. What’s next? Once you start changing the constitution, you leave room for other things to occur. Being a part of an oppressed race, I really have a hard time understanding how the AA community could place the same restrictions on another group. It’s nobody’s business who people go to bed with at night or who they wake up with in the morning. I’m saddened and disheartened by this. I especially don’t trust the right wing nuts who use religion as an excuse to brainwash people. When a religious group tells you that voting for Obama will bring a holocaust, it’s time to rethink who guides us in life. I hope the gay and lesbian community fight until the very end and succeed because injustice anywhere is a threat to justice everywhere.
Thank you, MH.
I’m glad to see that there’s someone on here who understands how statistics works and doesn’t think that a sample needs to be a large fraction of the population it’s drawn from to be good enough for a reasonable confidence interval.
That shockingly common misunderstanding is one of my pet peeves, and it really shows when someone has no clue about statistics.
Look, I understand a Bayesian interval in relation to ONE binary value. Perhaps someone who HAS a clue might be able to tell me how you can use it to draw an accurate conclusion about two separate sets of data. Is this related to fiducial inference? Can any of you apparent wizards explain THAT? Or direct me to a helpful book on the subject whereby I can then see the light? Thanks.
Though the sample size may be sufficient, age and county of residence seem to be major factors in how the state voted. Though all other racial group vote percentages were broken down by age, the exit poll does not give African American vote percentages by age. A poll heavily weighted toward older voters may generate a dramatically skewed result. (59% of whites over 65 voted yes, 67% of whites 18-29 voted no). Prop 8 won in all but coastal counties and a few bordering Nevada. From which counties were the African American respondents? Poll doesn’t say. Are the 225 or so African Americans polled truly representative of the 1.1 million that voted? Maybe, but, I’m not convinced.
http://www.cnn.com/ELECTION/2008/results/polls/#CAI01
I believe this is the data referred to in the article.
[…] support from the African American voting population that was turned out by Barack Obama, and questions about how viable that connection is. There is also, of course, the ongoing question about whether […]