摘要：Hagopian et al. (2013) published a headline-grabbing estimate for the Iraq war of half a million excess deaths , i.e. deaths that would not have happened without the war. We reanalyse the data from the University Collaborative Iraq Mortality Study and refute their dramatic claim. The Hagopian et al. (2013) estimate has four main defects: i) most importantly, it conflates non-violent deaths with violent ones; ii) it fails to account for the stratified sampling design of the UCIMS; iii) it fully includes all reported deaths regardless of death certificate backing, even when respondents say they have a death certificate but cannot produce one when prompted; iv) it adds approximately 100,000 speculative deaths not supported by data. Thus, we reject the 500,000 estimate. Indeed, we find that the UCIMS data cannot even support a claim that the number of non-violent excess deaths in the Iraq war has been greater than zero. We recommend future research to follow our methodological lead in two main directions; supplement traditional excess death estimates with excess death estimates for non-violent deaths alone, and use differences-in-differences estimates to uncover the relationship between violence and non-violent death rates.
