General Discussion
In reply to the discussion: So tired of the Gore won popular vote, Bush won electoral vote meme [View all]EX500rider
(10,847 posts)November 20, 2004.
"Criticism and suggestions by peer reviewer Sheila M Bird, MRC Biostatistics Unit, Cambridge CB2 2SR, UK, chair of the Royal Statistical Society's Working Party on Performance Monitoring in the Public Services. Calls scientific method "generally well described and readily repeatable", but says "particular attention is needed to the methodology for randomly selecting the location(s) of cluster(s) within governorates. Roberts and colleagues describe this rather too succinctly". Suggests additional information be included so that more precise multipliers (to obtain the final estimate) can be applied. Discusses an example hypothetical circumstance incorporating said information, regarding airstrike deaths and collateral damage, under which over-counting could occur due to population density variances among cluster representations."
March 26, 2005. "Criticism by Stephen Apfelroth, Department of Pathology, Albert Einstein College of Medicine. Criticizes "several questionable sampling techniques that should have been more thoroughly examined before publication" and lists several flaws, including a "fatal" one, that "In such a situation, multiple random sample points are required within each geographic region, not one per 739000 individuals."
"Debarati Guha-Sapir, director of the Centre for Research on the Epidemiology of Disasters in Brussels, was quoted in an interview for Nature.com saying that Burnham's team have published "inflated" numbers that "discredit" the process of estimating death counts.
She has some methodological concerns about the paper, including the use of local people who might have opposed the occupation as interviewers. She also points out that the result does not fit with any she has recorded in 15 years of studying conflict zones. A subsequent article co-authored by Guha-Sapir and Olivier Degomme for CRED reviews the Lancet data in detail. It concludes that the Lancet overestimated deaths and that the war-related death toll was most likely to be around 125,000 for the period covered by the Lancet study, reaching its conclusions by correcting errors in the 2006 Lancet estimate and triangulating with data from IBC and ILCS."
"Beth Osborne Daponte, a demographer known for producing death estimates for the first Gulf War, evaluates the Lancet survey and other sources in a paper for the International Review of the Red Cross.[36] Among other criticisms, Daponte questions the reliability of pre-war estimates used in the Lancet study to derive its "excess deaths" estimate, and the ethical approval for the survey. She concludes that the most reliable information available to date is provided by the Iraq Family Health Survey, the Iraq Living Conditions Survey and Iraq Body Count."
"Mark van der Lann, professor of biostatistics and statistics at UC Berkeley, disputes the estimates of both Lancet studies on several grounds in a paper co-authored with writer Leon de Winter. The authors argue that the confidence intervals in the Lancet study are too narrow, saying, "our statistical analysis could at most conclude that the total number of violent deaths is more than 100.000 with a 0.95 confidence but this takes not into account various other potential biases in the original data." Among the main conclusions of their evaluation are that "the estimates based upon these data are extremely unreliable and cannot stand a decent scientific evaluation. It may be that the number of violent deaths is much higher than previously reported, but this specific report, just like the October 2004 report, cannot support the estimates that have been flying around the world on October 29, 2006. It is not science. It is propaganda."
"Borzou Daragahi Iraq correspondent for the Los Angeles Times, in an interview with PBS, questioned the study based on their earlier research in Iraq, saying, "Well, we thinkthe Los Angeles Times thinks these numbers are too large, depending on the extensive research we've done. Earlier this year, around June, the report was published at least in June, but the reporting was done over weeks earlier. We went to morgues, cemeteries, hospitals, health officials, and we gathered as many statistics as we could on the actual dead bodies, and the number we came up with around June was about at least 50,000. And that kind of jibed with some of the news report that were out there, the accumulation of news reports, in terms of the numbers killed. The U.N. says that there's about 3,000 a month being killed; that also fits in with our numbers and with morgue numbers. This number of 600,000 or more killed since the beginning of the war, it's way off our charts."
"A 2010 paper by Professor Michael Spagat entitled "Ethical and Data-Integrity Problems in the Second Lancet Survey of Mortality in Iraq" was published in the peer reviewed journal Defense & Peace Economics. This paper argues that there were several "ethical violations to the survey's respondents", faults the study authors for "non-disclosure of the survey's questionnaire, data-entry form, data matching anonymised interviewer identifications with households and sample design", and presents "evidence relating to data fabrication and falsification, which falls into nine broad categories." The paper concludes that the Lancet survey, "cannot be considered a reliable or valid contribution towards knowledge about the extent of mortality in Iraq since 2003."