Lancet Iraq survey methodology under fire
- 19 Oct 06, 04:53 PM
Over the last couple of days two new themes have emerged in the debate over the Lancet/Johns Hopkins University report which estimated an excess 601,000 violent deaths in Iraq as a result of the invasion...
The first, here, maintains that there was a flaw in the methodology because the number of clusters sampled was too low. The Lancet study sampled from 47 clusters of families; Steven Moore, a political consultant writes:
"Appendix A of the Johns Hopkins survey, for example, cites several other studies of mortality in war zones, and uses the citations to validate the group's use of cluster sampling. One study is by the International Rescue Committee in the Democratic Republic of Congo, which used 750 cluster points. Harvard's School of Public Health, in a 1992 survey of Iraq, used 271 cluster points. Another study in Kosovo cites the use of 50 cluster points, but this was for a population of just 1.6 million, compared to Iraq's 27 million."
A second criticism is set to emerge in tomorrow's Science magazine where academics from Royal Holloway and Oxford will say that the study suffers from "main street bias" - in that sampling the families near main thoroughfares leads to an unnaturally high number of casualties because - with car bombs, driveby shootings etc - that is where they occur.
Both these critiques will raise questions not just for the researchers but for the peer review process leading to publication. We will try to keep you informed as to the answers, and the debate as it unfolds, here on the Newsnight blog.