Arnold Kling  

The Perils of Amateur Epidemiology

Arnold Kling with a Minus Sign... Further Advice for a Future Re...

Robin Hanson cites one paper that says that higher unemployment reduces mortality, perhaps because of healthier eating, while another paper says that higher unemployment reduces the consumption of fruits and vegetables. He writes,

Either we can cross "eat healthier" off the list of possible ways unemployment helps health, or maybe fruits and veggies aren't as healthy, and fast food as unhealthy, as we suppose.

Epidemiology is a difficult topic. I think that if economists are going to contribute anything to the field, it not be by doing studies based on regression methods. If anything, we should contribute skepticism about such methods, based on what we have learned about the biases caused by specification searches, data mining, and the bias toward publishing only "significant" effects (that bias itself undermines the reported significance). Instead, look for natural experiments, and don't forget to be skeptical of those, too.

For example, this study of miscarriages was focused on the effect of caffeine intake. You can compare the incidence of miscarriages among caffeine drinkers and non-caffeine drinkers, but other factors may confound. The abstract says that it uses "multivariate analysis" to try to deal with confounding factors, such as smoking.

However, there is a possible natural experiment, based on nausea. Some women become nauseous during pregnancy, while others experienced much less discomfort. Women who become nauseous during pregnancy will greatly reduce their caffeine intake. If we see that nausea reduces the incidence of miscarriages for those women more than for women who don't drink caffeine in the first place, then we can implicate caffeine as a factor in causing miscarriages.

Comments and Sharing

CATEGORIES: Economic Methods

COMMENTS (4 to date)
Rob writes:

That's a good one. Protect instrumental variables with your life though. They are the road to a happy tenure appointment

Lucas Reis writes:

"...maybe fruits and veggies aren't as healthy (...) as we suppose."

We suppose many wrong things about food, really. The science is not as developed as common sense think it is.

I read a book about it these days, "Good Calories, Bad Calories", by Gary Taubes, and it's great in showing how little we know about our food. Strongly recommended!

Ray writes:

Lucas stole my thunder.

Taubes' books are very good (he just released a second book that builds on 'Good Calories, Bad Calories' called 'Why We Get Fat').

I'm not new to the overall subject of health and fitness, and Taubes is spot on. They're not diet books by the way. His first is an in depth investigation of how we got to the befuddled state we're in now with health and diet, and the second one is basically an extension of the first, but brought down in to layman's terms.

KM writes:

I have not read the book by Taubes, but it seems like he is saying what more and more are arguing right now, i.e. carbohydrates is the big problem (sugar, white flour, rice, bread etc).

I don't think the science in the field of nutrition is going be better with more work by economists or epidemiologists. What that field needs is more well-conducted RCTs. And the recent RCTs evaluating different eating habits tend to indicate that you should feel free to eat more fat (aviod low-fat product) and be very moderate in consumption of carbohydrates (that includes sweet fruit).

A lot of diabetic patients have been able to stop taking medication completely by changing to LCHF food (low-carb high-fat).

Comments for this entry have been closed
Return to top