Political Animal

STILL MORE ON LOTT….IT JUST

STILL MORE ON LOTT….IT JUST NEVER ENDS….Lott says he did his survey during the first few months of 1997. His hard disk crashed in June 1997 and he lost all the data.

OK, fine. But it’s not believable that he had already thrown away the paper records within ten weeks of finishing the survey. And when his computer crashed, it would have been extra important to keep all his backup data, right? I mean, if your computer crashed, wouldn’t you take extra care to make sure that you held on to any raw paper records that you had?

I would. So what’s his story? Were the paper records already gone by June? Why? And if they were still around at that point, why were the results not recreated?

EVEN MORE ON LOTT….Here are

EVEN MORE ON LOTT….Here are the demographic questions that Lott used for a survey he conducted recently to reproduce the results of his mysterious 1997 survey. He claims that it is very similar to the one he did in 1997:

(We obviously have the area code, write down sex from the voice if possible.)

I have two demographic questions for the survey.

What is your race? black, white, Hispanic, Asian, Other.

What is your age by decade? 20s, 30s, 40s, so on.

That’s it? And from that he was able to weight responses up or down by as much as 4:1, magically morphing 2 out of 25 respondents from 8% down to 2%?

Look: the purpose of weightings is to ensure that your sample is similar to the demographics of the United States as a whole. So if your sample contained, say, 11% blacks, but blacks are actually 12% of U.S. population, then you would weight the black responses a little more heavily so that they constitute 12% of the total survey responses.

But weights like that are very small, only a few percentage points. Lott’s response, basically, is that “black Vermonters,” for example, are very uncommon. So if such a person ended up in his survey, he would represent .04% of the survey sample (1 out of 2,424), while he represents only .01% of the general population. Thus, that one response would need to be downweighted 4:1.

This is simply ridiculous. Even the most partisan hack wouldn’t try to get away with something like that.

Why does anybody believe this stuff?

JOHN LOTT….THE SAGA CONTINUES….One of

JOHN LOTT….THE SAGA CONTINUES….One of the interesting notes at the bottom of Kieran Healy’s post about John Lott yesterday was this:

One point came up which I haven’t seen mentioned before: if Lott did the survey while at the University of Chicago, why didn’t he go through their Institutional Review Board? Federal Law says you can’t conduct any research involving human subjects without first obtaining IRB approval. Does the Chicago IRB have any record of Lott going through Human Subjects review? Has he given any reason why he didn’t?

This struck me as peculiar, but Kieran confirmed via email that he meant what he said: this stuff is important, and survey work does count as human subject research. “You can get yourself (and worse, your whole academic unit) into serious shit if you don’t do the paperwork.”

Today Ted Barlow makes the same point:

For my undergraduate thesis, we interviewed less than 50 participants and produced no less than two boxes of paper. We had to have our methodology reviewed, because we were working with human participants….

So is there any record of Lott getting permission from his IRB?

And ArchPundit makes another point that I’ve been noodling about myself: surveys are very time consuming things. I’ve done lots of telephone survey work, and if you’re not working with professionals using predictive dialing equipment (which he wasn’t), you’re lucky to be able to make 20 calls per hour. In fact, that would be pretty optimistic.

So: 2,424 respondents means probably around 10,000 phone calls. That means 500 hours of calls. I doubt that students could manage to fit in more than 10 hours a week of calls, so this means at least 50 man weeks of phone calls, and that doesn’t even count all the work of transcribing the results into a statistical package, doing the weighting he claims to have done, and then producing the final results. And all of that just vanished into thin air?

And don’t forget: Lott originally sourced the 98% number to someone else and then changed his mind only in 1999 when it turned out that he had misinterpreted the survey results he was using. He had never mentioned doing a survey of his own until then. What’s more, Lott’s first reference to the 98% number was in early 1997, well before his survey could have been finished.

This is nonsense, and the sample weighting is nonsense too. In fact, the whole thing sounds like a tissue of lies from beginning to end. Knowing what we now know about his obsessive and deceptive “Mary Rosh” persona, can anyone possibly read James Lindgren’s extremely detailed investigation into this affair and conclude anything else?

AMAZON PROFITS….Yesterday Amazon reported fourth

AMAZON PROFITS….Yesterday Amazon reported fourth quarter results: revenues of $1.4 billion ? up from last year ? and a tiny profit of $3 million ? down from last year. And of course there was also the usual “pro forma” malarky: we would have earned $75 million if we didn’t have to, you know, follow normal accounting rules and all.

This has gotten ridiculous. Amazon is the biggest and most successful of the Internet retailers, and yet they can’t show more than a microscopic profit at an annual run rate of nearly $6 billion. If you can’t manage a profit at that level, when can you?