In response to my blogging about dubious nature of statistical significance, a terrific young scholar, Lisa Herzog (Oxford), calls my attention to a neat piece in The Atlantic. My favorite line in the piece: “The odds that anything useful will survive from any of these studies are poor,” says Ioannidis—dismissing in a breath a good chunk of the [medical] research into which we sink about $100 billion a year in the United States alone."
Much empirical research (in medicine and economics, as the piece rightly notes) is basically no more than data-mining. In the absence of well confirmed background theory (a rarity in all the sciences) this is nearly worthless. As I pointed out a while back, 'results' come too easily in modern social science. Evidence based medicine (which is the most important technical fad in medical science), is just most sophisticated form of data mining.
Recent Comments