14 February 2011

How problems in WTUs are like drug interaction deaths

Medical issues in the military seem to be getting a lot of press attention these days, so I feel it's important to take a look at the genesis of these problems, specifically the polypharmacy issue and the troubles with Warrior Transition Units (WTUs). The policies leading to these problems have been well intentioned, yet there seems to be little thought or care for how and why they've gone so far astray, although there is plenty that they have gone astray.

Before delving into the issues I mentioned above, let's use a more well known example of these "second order effects." During the toughening of drug sentences in the late 1980s the Anti-Drug Abuse Act made prison sentences proportional to the quantity of illicit substance that a dealer was holding when arrested. The thinking behind such laws is straightforward: stiffer sentences for bigger time drug dealers. At first blush this sounds like a solid enforcement strategy; however, both in theory and in practice these laws had the unintended consequence of incentivizing dealers to hold smaller quantities while still being able to meet demand. Dealers responded to this by placing a new premium on purity. If they could sell their customers half the weight for the same price, they faced a lighter sentence if/when they were arrested. In this way drug laws that were designed to curtail large scale drug dealing had the perverse effect of increasing drug purity, which itself has many second order consequences (higher overdose rates, increased addiction potential, etc).

12 February 2011

Opinion as journalism in the NYT

The NYT has an opinion piece (although it's filed as news) decrying the ideological dominance of the social sciences by liberals. Fortunately for ivory tower liberals everywhere, the piece would be bad as opinion. It's truly awful as journalism. Let's begin where the article does:
“Anywhere in the world that social psychologists see women or minorities underrepresented by a factor of two or three, our minds jump to discrimination as the explanation,” said Dr. Haidt, who called himself a longtime liberal turned centrist. “But when we find out that conservatives are underrepresented among us by a factor of more than 100, suddenly everyone finds it quite easy to generate alternate explanations.”
People do often jump to discrimination as a default explanation for gender discrimination (particularly in graduate schools). However, as the article itself goes on to explain statistics demonstrate that the disproportionate number of men in graduate studies actually represents discrimination against the men, since women are, as compared to the percentage of applicants, overrepresented.

08 February 2011

You do not understand what a p-value is (p < 0.001)

I'm sure it's only a matter of weeks (months at most) before every "news" publication in this country runs a story on the pitiful state of statistical rigor in research. Most of them will probably point to one of a handful of studies that pick apart the various statistical methods used in studies. None of them will point out the fundamental statistical misunderstanding that undergirds 99% of the medical literature: the p-value and what it means. The p-value is so misunderstood, and the misunderstanding so widespread, that my medical school class was taught the wrong definition.

Here's what the p-value is not: "The probability that the null-hypothesis was true." I didn't choose this definition out of thin air to beat up on, it was the correct answer on a test I took asking, "Which of these is the definition of a p-value?" Beyond that it's what most people think a p-value is.