Friday, November 12, 2004

Super Gerard

Gerard at American Digest is so essential that I link to him with the assumption that anyone who ends up here would necessarily read his page too, but here goes anyways. First, the garment of choice for those who believe the 2004 vote was rigged, and then a really choice gaggle of mini-posts, which include a bit about an article that examines recent claims of 100,000 Iraqi civilian casualties since the war began. An excerpt:

Imagine reading a poll reporting that George W. Bush will win somewhere between 4 percent and 96 percent of the votes in this Tuesday's election. You would say that this is a useless poll and that something must have gone terribly wrong with the sampling. The same is true of the Lancet article: It's a useless study; something went terribly wrong with the sampling.

The problem is, ultimately, not with the scholars who conducted the study; they did the best they could under the circumstances. The problem is the circumstances. It's hard to conduct reliable, random surveys—and to extrapolate meaningful data from the results of those surveys—in the chaotic, restrictive environment of war.

However, these scholars are responsible for the hype surrounding the study. Gilbert Burnham, one of the co-authors, told the International Herald Tribune (for a story reprinted in today's New York Times), "We're quite sure that the estimate of 100,000 is a conservative estimate." Yet the text of the study reveals this is simply untrue. Burnham should have said, "We're not quite sure what our estimate means. Assuming our model is accurate, the actual death toll might be 100,000, or it might be somewhere between 92,000 lower and 94,000 higher than that number."

Not a meaty headline, but truer to the findings of his own study.


To which Gerard astutely adds, "In the waning days of the election, one big gun fired without stop over the heads of the voters was the '100,000' dead citizens of the Iraq meme. Besides the obvious fact that we have not seen the 186 funerals every day reported for even one day, the study on which the lie was based was also deeply flawed. For political purposes? Almost certainly. After all it is much easier to hide bias inside statistics than to hide it in editorial columns." (emphasis mine)

Devastating. Before logic, the witchcraft that liberals bring to bear on the issues of the day melts away. If the mainstream press were genuinely interested in giving the American people the tools to separate useful from useless, such nonsense would be much harder to perpetrate.

No comments: