So much for the Lancet's "massive Iraqi civilian death" study

July 28, 2007  ·  Michael Fumento  ·  Weblog

Remember the Lancet study in 2004 claiming that "about 100,000 excess deaths, or more have happened since the 2003 invasion of Iraq," and that "Violence accounted for most of the excess deaths and air strikes from coalition forces accounted for most violent deaths?"

I wrote on this as soon as it appeared, observing that several indicators showed it was a piece of crock. But others did much more in-depth analyses, including Shannon Love at Chicago Boyz. He has now found out via Michelle Malkin and Instapundit that a forthcoming study by David Kane, Institute Fellow at the Institute for Quantitative Social Science at Harvard University, shows just how wrong the original study was. Love notes among other things that that "if the Falluja cluster is included in the statistical calculations, the confidence interval dips below zero" meaning that it loses statistical significance. Without statistical significance, the findings mean nothing,

I claimed at the time the "100,000 death study" was pure politics (It came out right before the presidential election) and intentional deception on the part of the authors and the Lancet editor himself and there's no reason to think otherwise now.

Incidentally, as I was putting this blog together I accidentally posted it, making Love's words look like my own. Mea culpa.