Remember the famous Lancet report which caused such a stir in 2006? The one that argued more than 10 times as many Iraqis had died since 2003 than any other source (pro-government or anti-war) had previously alleged? The one that was more or less accepted uncritically by opponents of the Iraq War? There were serious methodological concerns with the report in 2006, but the National Journal has done a great job of compiling all those concerns in this article.
Officials at Iraq Body Count strongly opposed the Iraq war yet issued a detailed critique of the Lancet II study. Researchers wading into a field that is this fraught with danger have a responsibility not to be reckless with statistics, the group said. The numbers claimed by the Lancet study would, under the normal ratios of warfare, result in more than a million Iraqis wounded seriously enough to require medical treatment, according to this critique. Yet official sources in Iraq have not reported any such phenomenon. An Iraq Body Count analysis showed that the Lancet II numbers would have meant that 1,000 Iraqis were dying every day during the first half of 2006, "with less than a tenth of them being noticed by any public surveillance mechanisms." The February 2006 bombing of the Golden Mosque is widely credited with plunging Iraq into civil war, yet the Lancet II report posits the equivalent of five to 10 bombings of this magnitude in Iraq every day for three years.
"In the light of such extreme and improbable implications," the Iraq Body Count report stated, "a rational alternative conclusion to be considered is that the authors have drawn conclusions from unrepresentative data."
This will not make the headlines in the same way that the Lancet's shoddy contribution to the Iraq War debate did. (Thanks, CK)