 |
 |
Clapp's paper has almost no information on what he found for PD. The discussion is limited to the single sentence: "Statistically increased PMRs for multiple sclerosis, Parkinson's disease, and amyotrophic lateral sclerosis contributed to the excess for diseases of the nervous system." It does not show the numbers of cases found or what statistical method was used or anything else about the PD data. The whole paper is also silent on how they corrected for multiple comparisons, if they did. Multiple comparisons refers to the issue of making many comparisons using the same data set. For example, here the authors did statistical tests for 69 specific causes of death in both sexes, for a total of 138 discrete comparisons, as well as a number of aggregate disease categories such as "non-malignant respiratory disease" or "cancer of bladdder and other urinary organs". If each comparison has a 5% false-alarm rate, one would expect to see several spurious cases of "statistical significance". Also, IBM has apparently prepared a technical critique of the study, but it has not been published. Not even a summary has been released. I would withhold judgement until the critique and the author's response are available. In short, with respect to PD, there is a suggestive hint but nothing solid to rely on. > ... as it related to pd, does anyone have an opinion on this > article? > >joan > > Subject: gasslist: Cancer - IBM computer factory workers show > markedly increased cancer death rates, says >researcher ---------------------------------------------------------------------- To sign-off Parkinsn send a message to: mailto:[log in to unmask] In the body of the message put: signoff parkinsn