A publication called New Scientist has what sounds like a man-bites-dog story, also touted by ABC News (hat tip: Bill Kriebel), under the headline "Porn in the USA: Conservatives Are Biggest Consumers." It turns out there is far less to this than meets the eye--and bizarrely, that becomes clear in the opening paragraphs:
Americans may paint themselves in increasingly bright shades of red and blue, but new research finds one thing that varies little across the nation: the liking for online pornography.
A new nationwide study (pdf) of anonymised credit-card receipts from a major online adult entertainment provider finds little variation in consumption between states.
....
Finally, in paragraph four, we get to the "news":
However, there are some trends to be seen in the data. Those states that do consume the most porn tend to be more conservative and religious than states with lower levels of consumption, the study finds.
"Some of the people who are most outraged turn out to be consumers of the very things they claimed to be outraged by," Edelman says.
You can see why this "finding" appeals to journalists. It is counterintuitive, while at the same time reinforcing a disparaging liberal stereotype of conservatives: that their moralistic attitudes about sex reflect their own repressed desires. Really, though, this is far more compelling as an example of how journalists, egged on by attention-seeking scholars, misuse science by overstating its conclusions to fit their own preconceptions.
A look at the actual study--available here, though ABC omits the link--shows that it is far from conclusive. Edelman used data from only one adult-entertainment company. He concedes that "it is difficult to confirm rigorously that this seller is representative" and makes no evident effort to do so. And contrary to his New Scientist quote, the study tells us nothing about "the people who are most outraged."
Such correlations as he finds are only among states and ZIP codes. New Scientist touts the finding that John McCain carried "eight of the top 10 pornography consuming states" to justify the headline's conclusion that "Conservatives Are Biggest Consumers."
To understand why this is a non sequitur, look at the Census Bureau's report on the black population, and specifically the state-by-state table on page 4. The four states with the most blacks as a percentage of population--Mississippi, Louisiana, South Carolina and Georgia--all went for McCain. By Edelman's logic, this would point to the conclusion that blacks are the most reliable GOP voters. The reality, of course, is more complex: Blacks in fact overwhelmingly vote Democratic, and states in the Deep South tend to have both large black populations and very conservative white voters.
Even given all that, however, Edelman's findings don't amount to much, as he explains in the concluding paragraph of his study:
On the whole, these adult entertainment subscription patterns show a remarkable consistency: all but eleven states have between two and three subscribers to this service per thousand broadband households, and all but four have between 1.5 and 3.5. With interest in online adult entertainment relatively constant across regions, there's little sign of a major divide.
Indeed, Utah has only 1.69 subscriptions per thousand people. The Beehive State's population is 2.7 million, according to the latest census estimate. That means the total number of Utahns who subscribe to the porn service Edelman analyzes is less than 5,000--quite a small number on which to conclude that the place is full of moralistic deviants.
Statistics can be very hard, with lots of non-obvious ways to go wrong.
No comments:
Post a Comment