Last week I blogged about a study from Washington University linking gas prices to obesity. The study proclaimed that for every $1 rise in a gallon of gas, we should see a 15% drop in obesity levels over five years, because people would walk or ride bikes more, and they'd have less money to eat fatty restaurant food.
I mocked the study. I mean, look around. Gas prices have spiked and people are getting fatter. But I was especially snarky about the part claiming that the rise in obesity between 1979 and 2004 was due to FALLING gas prices (I'm still trying to do the inflation-adjusted math to see how they've fallen, but, whatever).
Well I heard from the study's author, Charles Courtemanche, who didn't care much for my sarcasm. More importantly, though, he pointed out that I got the story wrong! His study found that the rise in obesity since '79 IS ONLY 13% DUE TO LOWER GAS PRICES. The other 87% is due to factors like those I pointed out--super-sized meals and a higher standard of living.
He writes: "I'm disappointed that a respected journalist would write an article like this without even spending two minutes fact-checking her story. I do not appreciate being made to look like an idiot on national news, especially for something I never said. I would appreciate a correction or apology, although I'm not holding my breath."
Charles! Hold your breath! You don't know me very well! First of all, you may be the first person who's ever referred to me as a "respected journalist." Thank you for that! Ok, you can now exhale--I'm sorry I didn't get the whole story straight, and I hope this blog clears that up.
Here is a summary of Courtemanche's thesis: A causal relationship between gasoline prices and obesity is possible through mechanisms of increased exercise and decreased eating in restaurants. I use a fixed effects model to explore whether this theory has empirical support, finding that an additional $1 in real gasoline prices would reduce obesity in the U.S. by 15% after five years, and that 13% of the rise in obesity between 1979 and 2004 can be attributed to falling real gas prices during this period. I also provide evidence that the effect occurs both by increasing exercise and by lowering the frequency with which people eat at restaurants.
However, even with the correction, I'm still arching one brow in wonder at how such numbers are calculated. I'm afraid my sarcasm remains intact. So does my fallibility. You're only as good as the accuracy of your last story.
Comments? Funny Stories? Email firstname.lastname@example.org