A recent study suggesting a link between coffee drinking and longer lives has prompted a flurry of coverage—some snarky, some cautious, but mostly celebratory. (We see you there, reaching for another cup of coffee.)
The study published at the prestigious New England Journal of Medicine is about as good as observational epidemiology studies go, but it’s limited by virtue of being observational. Last month on our Crux blog, Gary Taubes wrote a hard-hitting piece about the problems with observational studies. A major limitation of surveying people about their lifestyle habits is that correlation does not imply causation. It can’t prove coffee drinking actually led to living longer. There are always confounding variables.
In this coffee study, for example, they initially found that coffee drinkers died younger, but coffee drinkers are also more likely to be smokers. When they controlled for smoking as a confounding variable though, the result flipped: coffee ...
