Friday, October 20, 2006

Scoop: Lancet Iraq Study Flawed: Death Toll Too High

Scoop: Lancet Iraq Study Flawed: Death Toll Too High: "Researchers at Oxford University and Royal Holloway, University of London have found serious flaws in the survey of Iraqi deaths published last week in the Lancet.

Sean Gourley and Professor Neil Johnson of the physics department at Oxford University and Professor Michael Spagat of the economics department of Royal Holloway, University of London contend that the study’s methodology is fundamentally flawed and will result in an over-estimation of the death toll in Iraq.

->The study suffers from 'main street bias' by only surveying houses that are located on cross streets next to main roads or on the main road itself. However many Iraqi households do not satisfy this strict criterion and had no chance of being surveyed.

->Main street bias inflates casualty estimates since conflict events such as car bombs, drive-by shootings artillery strikes on insurgent positions, and market place explosions gravitate toward the same neighborhood types that the researchers surveyed.

->This obvious selection bias would not matter if you were conducting a simple survey on immunisation rates for which the methodology was designed.

->In short, the closer you are to a main road, the more likely you are to die in violent activity. So if researchers only count people living close to a main road then it comes as no surprise they will over-estimation of the death toll in Iraq.

->The study suffers from "main street bias" by only surveying houses that are located on cross streets next to main roads or on the main road itself. However many Iraqi households do not satisfy this strict criterion and had no chance of being surveyed.

->Main street bias inflates casualty estimates since conflict events such as car bombs, drive-by shootings artillery strikes on insurgent positions, and market place explosions gravitate toward the same neighborhood types that the researchers surveyed.

->This obvious selection bias would not matter if you were conducting a simple survey on immunisation rates for which the methodology was designed.

->In short, the closer you are to a main road, the more likely you are to die in violent activity. So if researchers only count people living close to a main road then it comes as no surprise they will over count the dead."

2 comments:

Unknown said...

Iraqi Body Count has also come out with a press release and said this is a ridiculous survey. They made mention of the numbers of wounded that would be seeking medical help if there were deaths in numbers like this and said there was nothing to indicate these levels of violence are accurate.

But I have still seem some lefties supporting it. It is amazing how stupid people can be.

Morgan said...

I've seen many people supporting the study. They can't answer the criticisms of it, though.

The only way to counter the suggestion that there was bias toward densely populated areas/main streets would be for the researchers to release data regarding the actual neighborhoods suveyed. They haven't done so, though I doubt it would pose privacy problems if they did.

Likewise, the only was to counter the argument that freeing the "field manager" to choose alternative locations at his discretion may have introduced bias would be for the researchers to explain how these new neighborhoods were chosen or for them to show that the "alternative neighborhoods" were statistically indistinguishable from the randomly chosen ones. They have done neither.