Tuesday 17 May 2005

The Lancet report, again.

Everything I said about the Lancet study also applies to this new UN report. However, as Mr Cox rightly points out, it is likely to be less inaccurate than the Lancet study, because it involves better and larger sampling.

It is important to note that the confidence intervals of the Lancet report completely encapsulate the confidence intervals of the UN report, which means the two studies are not necessarily contradictory.

Well, of course. One study says there were probably between 8,000 and 194,000 deaths; the other says there were probably between 18,000 and 29,000 deaths. There's obviously no contradiction there. Unless, of course, you were foolish enough to interpret "probably between 8,000 and 194,000" as meaning "definitely at least 100,000". Then there's a huge bloody great contradiction. Oops.

Since, as we were repeatedly told, anyone who refused to accept the 100,000 figure did so because they were pro-war, it'll be interesting to see what the anti-war types make of this new figure, coming, as it does, from the UN. Expect conspiracy theories.

No comments: