October 20, 2006
I submitted a letter to the editors of the Wall Street Journal on October 18 regarding an opinion article by Steven E. Moore (“655,000 War Dead?,” October 18, 2006). Les Roberts submitted his own letter to address some of the statements inaccurately attributed to him by Mr. Moore in his article. We hope the paper will publish both responses shortly.
Mr. Moore did not question our methodology, but rather the number of clusters we used to develop a representative sample. Our study used 47 randomly selected clusters of 40 households each. In his critique, Mr. Moore did not note that our survey sample included 12,801 people living in 47 clusters, which is the equivalent to a survey of 3,700 randomly selected individuals. As a comparison, a 3,700-person survey is nearly 3 times larger than the average U.S. political survey that reports a margin of error of +/-3%.
Our study also produced a range of plausible values that reflect the margin of error in our estimate. These values are included in our study, which was published Oct. 11, 2006, in the peer-reviewed, scientific journal, The Lancet. Using our 47 clusters, we estimated that 655,000 excess deaths have occurred in Iraq since March 2003 within a range of plausible values from 393,000 to 943,000 deaths. Even our lowest estimate indicates that a significant amount of death has occurred in Iraq, which is not being measured by other surveillance methods, such as news accounts or counting bodies in morgues.
It is clear that using more clusters would have given our estimate a greater degree of precision, assuming we also increased our sample size. For example, had we used 470 clusters, our range of plausible values would have been about 3 times narrower. However, there is a trade off between obtaining meaningful data and ensuring the safety of our surveyors. Surveying more clusters would have also meant more risk to the survey team.
In addition, Mr. Moore claimed that the Hopkins study did not include any demographic data. The survey did collect demographic data, such as age and sex, related to violence, although they are not the same details Mr. Moore’s company would have collected for public opinion polls. The characteristics of households in our study are similar to other accounts of households in Iraq and the region, though the household size for the 2006 study is smaller (6.9) than found in the 2004 survey (7.9).
Mr. Moore apparently agrees with us that a cluster survey is the preferred approach to quantifying post-invasion violent deaths in contrast to counts of deaths from newspaper articles and morgues or not counting at all. We hope he will join us in our recommendations that an independent body with adequate resources monitor deaths among civilians in conflict—using scientific methods, as was done in our survey.