Last October The Lancet published an article claiming that almost 655,000 more Iraqis had died since the US-led invasion than would have died had the invasion not occurred. The article was immediately subjected to a barrage of criticism from around the world, and the authors promised to answer the questions and, in particular, to provide more detailed information on the methodology of the survey that formed the basis for their estimate. Have they done so?
One academic expert on statistical survey methodology says not. As a result, his doubts about the validity of the study are increasing.
Peter Lynn, Professor of Survey Methodology at the Institute of Social and Economic Research, University of Essex, has been quietly investigating and, despite several e-mails to the researchers, has been unable to get answers: “I can’t come out and say I support the paper, or say that it’s rubbish, because I haven’t been able to find out enough. But the fact that they are dragging their feet on answering my questions makes me sceptical.” Had the paper been submitted to a statistics journal instead, Professor Lynn says, it might not have survived peer review.
That final sentence makes an excellent point. Did The Lancet’s peer reviewers possess the knowledge of technical statistics and survey methodology needed to assess the research? After reading the article, I considered that a legitimate question.
I, along with many other statisticians, expressed serious reservations about the soundness of the survey and the reliability of the results. That The Lancet authors appear unwilling to answer basic questions that the original article’s inadequate documentation left unanswered only diminishes what credibility they have left. The unavoidable question now: Are they trying to hide something?
By the by, I have just received more material from other experts investigating The Lancet study, and I plan to post an item about that in the next day or two.
Previous related posts:
- “Main street bias” in Lancet study
- Lancet study of Iraqi deaths is statistically unsound and unreliable
UPDATE (5 Dec.): The promised post is here.









Posts

Renowned choral conductor and composer of carols