King at SCSU Scholars has updated his post attacking the Lancet study with a response to my post. He admits error on one point, but on the rest he has the nerve to accuse me of bringing biases rather than facts to the debate. To see who is bringing facts and who is bringing biases let’s look at one of the points he contests:
King originally claimed (my emphasis):
They also chose both to change their list of randomly sampled areas so they didn’t have to drive as much; this meant they stayed close to Baghdad and the Sunni triangle, probably oversampling high-casualty areas.
Note that reducing the driving doesn’t matter unless it biases the results of the study. King claimed that biases the results upwards by oversampling high-casualty areas. I responding by pointing out that they didn’t oversample high-casualty areas:
It is true that sampling was done in such a way as to reduce travel, but this does not mean that they stayed close to Baghdad. They paired Governates that were adjacent and had had similar levels of violence and only sampled from one (randomly chosen) of the pair. This produces no bias towards high-casualty areas.
According to King, that passage contains no facts, just my biases. Now look at how King responds (my emphasis):
See page 1858: “During September, 2004, many roads were not under the control of the Government of Iraq or coalition forces. Local police checkpoints were perceived by team members as target identification screens for rebel groups. To lessen risks to investigators, we sought to minimise travel distances and the number of Governorates to visit, while still sampling from all regions of the country.” No Basra and the marsh Arabs. Limited sampling of the Kurdish north (Arbil, for instance.)
Instead of sampling Basrah, they sampled neighbouring Missan (where marsh Arabs also live). If you look at the map (figure 1 in the study) you will see that Missan is not “close to Baghdad”. Instead of sampling Arbil they sampled neighbouring (and also Kurdish) Sulaymaniya. If you look at the map (figure 1 in the study) you will see that Sulaymaniya is not “close to Baghdad”.
One glance at the map (figure 1 in the study) shows that they did not stay “close to Baghdad”, but King continues to insist that they did.
King finishes with:
The Lancet article includes only one violent death of the 7438 preinvasion individuals they interview (see Table 3). That fact alone should indicate the lack of measurement of prison/torture chamber deaths under Saddam.
The Amnesty International Report on Iraq for 2002 estimates that there were scores of killings by Saddam. This number is too small to show up in a survey of the size of the Lancet‘s.
Update: Amazingly, King insists over and over again that they oversampled Sunni areas, despite the clear language of the study and Figure 1, seen to the right, that shows that their samples were not close to Baghdad and did not oversample Sunni areas.