Wednesday, April 28, 2010

Thought for the Day

The only people who participate in deciding whether a certain Military action was "worth it" are the people who survived the result. Sort of a skewed dataset if you ask me!

Friday, April 2, 2010

Lying

There is a lot of fuss being made over Veronique de Rugy's "study" claiming that stimulus funds were distributed disproportionately to Democratic Congressional districts. The skinny is that this is an aberration in the data, because funds delivered to state governments are reported as being delivered to the district the capital is in. This means that districts that contain Sacramento, Albany and so forth will appear to have funds they don't, because they will be disbursed by the state government to other districts through the programs funded by the stimulus package.

Nate Silver kicked off the fuss (via the Shrill One):


That de Rugy has testified before Congress on the basis of her evidence, and never paused to consider why the top five congressional districts on her list overlap with Sacramento, Albany, Austin, Tallahassee and Harrisburg, is mind-boggling. The presence of a state capital is the overwhelmingly dominant factor it predicting the dispensation of stimulus funds. This could have been discerned in literally five minutes if she had bothered to look at the apparent outliers in her dataset and considered whether they had anything in common -- a practice that should be among the first things that any researcher does when evaluating any dataset.

No it is not "mind-boggling." She lied to Congress. She worked up a "study" that appeared to support a lie she wanted to tell to Congress. And the reason she wanted to tell this lie to Congress was so that this idea, that Democratic districts had been, corruptly, disproportionately allocated funds, could become a story on Fox news, be repeated by Limbaugh, and, eventually hit the mainstream as a "controversy."

We have seen this before. Betsy McCaughey created the memes that took down the Clinton health care plan, by lying, plain and simple. She worked the same game this time around, only to be taken apart by a late night comedian. McCaughey had no interest in an honest assessment of the plans in either case, no interest in an actual policy debate, but rather wanted to get the "kill granny" meme going.

Nate's characterization of de Rugy's results as a "mind-boggling" error by a researcher is not only too polite, it advances her cause. Instead of a simple lie, this now becomes a conflict between academic researchers on both sides of the issue. And, by writing about it at all, Nate raises the profile of the claim.

There has been much praise of Nate for his devastating takedown. And if this were about a publication by a tenure-seeking professor, it would be so. But this is about someone trying to distort reality. By treating this garbage as worthy of extended analysis is to lend it more credence than it deserves. This deserved a six line dismissal, not a detailed analysis, and those six lines should have included the word "lie." Another possible response is a letter writing campaign to her dean at George Mason. Treating this as fodder for thoughtful analysis helps her attain both the short term goal of getting this meme out, and her personal goal of a permanent place on the wingnut welfare roll.