Wednesday, February 15, 2012

What's Wrong With the World: "How to Lie with Statistics, Example Umpteen"

Jeff and I hugely appreciate bloggers who delve into the more complicated PolitiFact-related issues.

Lydia McGrew of the "What's Wrong With the World" blog gives a proper dressing-down to the Obama administration, the Guttmacher Institute and our beloved PolitiFact over the supposedly "Mostly True" claim that 98 percent of Catholic women use birth control.

As is our wont, we'll focus primarily on PolitiFact's role in the mess.

McGrew:
(T)his Politifact evaluation of the meme gets it wrong again and again, and in both directions.

First, the Politifact discussion insists that the claim is only about women in this category who have ever used contraception. When I first heard that and hadn't looked at the study, I immediately thought of the fact that such a statistic would presumably include women who were not at the time of the study using contraception and had used it only once in the past. It was even pointed out to me that it would include adult converts whose use might easily have been prior to their becoming Catholic. However, that isn't correct, anyway. The study expressly was of current contraceptive use. That's, in a sense, "better" for the side that wants the numbers to be high.
McGrew pointed out earlier that the Guttmacher Institute study uses data for "women at risk for
unintended pregnancy, whom we define as those who had had sex in the three months prior to the survey and were not pregnant, postpartum or trying to get pregnant."  The women surveyed were additionally in the 15-44 age range.  Yet PolitiFact describes the findings like so:
We read the study, which was based on long-collected, frequently cited government survey data. It says essentially that — though the statistic refers specifically to women who have had sex, a distinction Muñoz didn’t make.

But that’s not a large clarification, since most women in the study, including 70 percent of unmarried Catholic women, were sexually experienced.
That's fact checking?

McGrew:
(O)n this point, too, the Politifact evaluation is completely wrong. Politifact implies that only the supplementary table on p. 8 excluded these groups and that Figure 3 on p. 6 included them! But this is wrong. The table on p. 8 is simply supplementary to Figure 3, and both are taken from the same survey using the same restrictions! This is made explicit again and again in the study.
McGrew's exactly right.  The same information accompanies the asterisk for each table (bold emphasis added):  "*Refers to sexually active women who are not pregnant, postpartum or trying to get pregnant."

It doesn't occur to PolitiFact that restricting the survey population like that throws a serious spanner in the works.

That kind of credulity goes by a different name:  gullibility.

Visit What's Wrong With the World and read all of McGrew's skillful fisking of the liberal trio.  It's well worth it.


Addendum:

The Guttmacher Institute drew its data ultimately from here.

It may be the case that the Guttmacher study is reliable.  Regardless of that, PolitiFact did virtually nothing to clarify the issue.  A recent Washington Post story does shed some light on things, however:
I called up Rachel Jones, the lead author of this study, to have her walk me through the research. She agrees that her study results do not speak to all Catholic women. Rather, they speak to a specific demographic: women between 15- and 44-years-old who have ever been sexually active.


Jeff Adds (2/15/2012): Over on PolitiFact's Facebook page, frequent PF critic Matthew Hoy offered up his usual spot on commentary:
I find [PolitiFact's] failure to note that the Alan Guttmacher Institute is closely allied with Planned Parenthood a troubling omission. It isn't some neutral observer and its studies shouldn't be taken at face value without some healthy skepticism.
This isn't the first time PolitiFact has ignored Guttmacher's relationship with Planned Parenthood. Regardless of the studies accuracy, the alliance deserves at least a cursory disclosure. It's also important to note that PolitiFact used a similar connection to justify the rating of Florida Governor Rick Scott's claim about high-speed rail projects:
Scott bases his claims on hypothetical cost overruns from a suspect study written by a libertarian think tank...We rate Scott's claim False.
We highlighted that rating here.



Correction 2/17/2012:  "Guttmacher" was misspelled in the next-to-last paragraph.

No comments:

Post a Comment