Tuesday, December 9, 2008

Correlation (not causation) of happiness

If those riding intellectual fads are sometimes guilty of sloppy reasoning, imagine what happens when two fads collide.

That’s what happened when the British Medical Journal elected to publish a study analyzing 1) happiness in 2) social networks. The study, by James Fowler and Nicholas Christakis, concludes that happiness is contagious within social networks. ... Indeed, according to Fowler, “if your friend’s friend’s friend becomes happy, that has a bigger impact on you being happy than putting an extra $5,000 in your pocket.”

Unfortunately, it’s probably not true. Here’s the crux of the research: the authors show that your happiness is positively related to the happiness of your friends, and that this holds even after accounting for a number of other variables, including how happy you and your friends were a few years back. That’s correlation; what about causation?

There are (at least) three reasons why happiness is correlated within social networks. ... The third reason is perhaps the most likely: if you and I are friends, we are often subject to similar influences. If a buddy of ours dies, we’ll both be less happy. Or, less dramatically, if our favorite football team wins, we’ll both be happier. But this isn’t contagious happiness — it is simply a natural outcome of the shared experiences of people in the same social circles.

Interestingly, the same issue of the BMJ contained a very careful article by Ethan Cohen-Cole and Jason Fletcher making precisely this point. They employ a pretty cheeky research strategy: if you want to show that a research design is silly, show that it leads to silly conclusions.

They use Fowler and Christakis’s approach on another dataset, and show that it leads to the unlikely conclusion that height, headaches, and acne are also contagious. The more likely explanation, of course, is that all are subject to similar environmental influences.
--Justin Wolfers, Freakonomics blog, on why it's not true that your spouse's happiness matters less for your own happiness than a complete stranger's

No comments: