EpiWonk reanalyzes the dataset that DeSoto and Hitlan played with

One of the great “myths” of the mercury militia, that movement that insists no matter what the actual scientific evidence shows that it absolutely, positively has to be mercury from vaccines that cause autism is the Myth of the Poor Excretor. In other words, the claim is that autistic children are somehow “poor excretors” of mercury, thus making the mercury that used to be in vaccines more toxic to them so that it gave them autism. One of the key pieces of evidence cited to counter this myth is a study by Ip et al (2004) that failed to find any correlation between hair and blood mercury levels and autism. This dataset was “reanalyzed” by DeSoto and Hitlan last year, sparking David Kirby to gloat that the data had been analyzed all wrong and that it really was the mercury after all!

DeSoto and Hitland were roundly criticized on a number of blogs including Photon in the Darkness and Autism Street. Dr. DeSoto responded with a long and petulant FAQ, resulting in more criticism (1, 2, 3). It was a blogospheric food fight, and Dr. Desoto ended up looking like one of the extras in Animal House.

Now, however, in perhaps the most definitive critique of DeSoto and Hitlan’s “reanalysis” of the Ip et al dataset, EpiWonk weighs in. Her advice to Hitlan and DeSoto: They should actually look at the data before deciding upon what analyses to apply. She also points out in a polite way that I will turn blunt that DeSoto and Hitlan were not exactly clear in the paper about what analysis they used, leaving EpiWonk no choice but to infer it.

Best line:

I’m not making any assumptions about what DeSoto & Hitlan did or did not do in exploratory or preliminary analyses. But all I have to work with is what’s in the published paper. The paper is four pages long, yet only one 8-line paragraph is devoted to the main result. On the other hand, three relatively long paragaphs are devoted to lecturing Ip and colleagues on why they (Ip et al.) should have used a one-tailed test.

And:

We can conclude absolutely nothing about the association of ethylmercury in vaccines to autism from these data.