National Journal;

Published by The Lancet, a venerable British medical journal, the study [PDF] used previously accepted methods for calculating death rates to estimate the number of “excess” Iraqi deaths after the 2003 invasion at 426,369 to 793,663; the study said the most likely figure was near the middle of that range: 654,965. Almost 92 percent of the dead, the study asserted, were killed by bullets, bombs, or U.S. air strikes. This stunning toll was more than 10 times the number of deaths estimated by the Iraqi or U.S. governments, or by any human-rights group.
[…]
How to explain the enormous discrepancy between The Lancet’s estimation of Iraqi war deaths and those from studies that used other methodologies? For starters, the authors of the Lancet study followed a model that ensured that even minor components of the data, when extrapolated over the whole population, would yield huge differences in the death toll. Skeptical commentators have highlighted questionable assumptions, implausible data, and ideological leanings among the authors, Gilbert Burnham, Riyadh Lafta, and Les Roberts.
Some critics go so far as to suggest that the field research on which the study is based may have been performed improperly — or not at all. The key person involved in collecting the data — Lafta, the researcher who assembled the survey teams, deployed them throughout Iraq, and assembled the results — has refused to answer questions about his methods.
[…]
When it comes to the question of peer review, the study’s defenders sometimes seem to want it both ways. On the one hand, Roberts talks about the need “to step beyond peer review.” Yet the authors insist that their study was peer-reviewed extensively (if rapidly, in order to be published before the election). The authors also maintain that one of the reasons they went to The Lancet with these studies is its quick turnaround time.
Surprisingly, not one of the peer reviewers seems to have thought to ask a basic question: Are the data in the two studies even true? The possibility of fakery, editor Horton told NJ, “did not come up in peer review.” Medical journals can’t afford to repeat every scientific study, he said, because “if for every paper we published we had to think, ‘Is this fraud?’ … honestly, we would fold tomorrow.”

More links and reponse.