New Photos:

  New Ramblings:

  New Links:

Counter

Last Updated

 


Previous Posts





About the Blog

The thoughts and theories of a guy who basically should have gone to bed hours ago.

I know, I know - what's the point? But look at it this way - I stayed up late writing it, but you're reading it...

Let's call ourselves even & move on, OK?


Powered by Blogger

Monday, October 16, 2006

Another Lancet Report - Let the Misinterpretations Begin...


The new Lancet Report is out, and the media headlines are saying "Study estimates 655,000 deaths due to Iraq war."

The last time Lancet issued a report (November, 2004), the headlines said "Study estimates 100,000 deaths due to war." At the time, though, very few articles were talking about confidence factors. What the 2004 report actually said, was that with a 95% confidence factor, the number of excess deaths (deaths over and above the amount expected to die in the same time period prior to the war) was somewhere between 8,000 and 194,000. Quite a range, huh? At the time, this reflected the poor conditions in Iraq, the difficulty in collecting the data, the lack of a random sample, etc. In order to narrow the range of the estimate, researchers would have had to lower the confidence factor. Logic dictates that pinning the number of dead to a single number (100,000) makes the confidence factor approach zero. In other words, it was just as likely that 8,000 people had been killed as it was that 194,000 were killed, and we had absolutely zero confidence in a single number like 100,000.

This time around, the confidence ranges are better, but still large: Total excess deaths is estimated at somewhere between 392,979 and 942,636 (95% confidence factor again). Violent deaths are estimated at somewhere between 426,369 and 793,663. The report also re-examines the first 18 months of the war (the span used for the 2004 report), and has narrowed the estimate to somewhere between 69,000 and 155,000. Better, but still a ~50% swing in both directions from the publicized 100,000 number.

No matter, though. Years from now, the only thing we'll remember is "655,000 killed due to Iraq war." File this one away with the NIE that said the war was creating more terrorists, even though that's not what it said at all.

The report itself is only 8 pages long, but as is typical, most people will gladly read dozens of pages of commentary, rather than read the actual 8 pages in question. If we take the time, though, we notice Page 3, which provides the raw data from which the estimates were drawn. And when we look at the raw data, the numbers don't seem to add up:

Researchers interviewed 12,801 people in 1,849 households and recorded 629 deaths in the past 54 months. Of these, 82 (13%) occurred prior to the invasion, and 547 (87%) occurred after the invasion. Of the post-invasion deaths, the raw data says that 247 (46%) were non-violent (e.g., heart disease, cancer) and 300 (55%) were violent (e.g., gunfire, explosive device, car bomb).

Now, if the 629 deaths, extrapolated across all of Iraq, comes to an estimated 654,965, then the number of post invasion, violent deaths should be 654,965 x 87% x 55%, which is 313,400 (as opposed to the 601,027 that is mentioned in the oft-quoted report summary). Either I'm missing something big here, or something is drastically wrong. Either way, I'm amazed that no one in the blogosphere has noted and/or explained this discrepancy...

posted by Brian at 2:29 PM


0 Comments:

Post a Comment

<< Home