[Previous entry: ""] [Main Index] [Next entry: ""]

09/22/2004 Archived Entry: "Gordon on The Health Hoax"

Gordon writes, Once one gets past its inflammatory title ["The Great Health Hoax"], this article by Robert Matthews provides a good explanation of why medical study after medical study claiming results that are "highly statistically significant" fail to deliver comparable results once they are put into general practice: The medical community's continued reliance on so-called "statistical significance tests" that do not in fact measure anything "significant."

To quote the article, " In 1992, trials in Scotland of a clot-busting drug called anistreplase suggested that it could double the chances of survival [after a heart attack]. A year later, another "miracle cure" emerged: injections of magnesium, which studies suggested could also double survival rates. Leading cardiologists hailed the injections as an "effective, safe, simple and inexpensive" treatment that could save the lives of thousands. But then something odd began to happen. In 1995, the Lancet published the results of a huge international study of heart attack survival rates among 58,000 patients - and the amazing life-saving abilities of magnesium injections had simply vanished. Anistreplase fared little better: the current view is that its real effectiveness is barely half that suggested by the original trial."

The article also has a reasonable layperson's account of the history of probability, from its orginal foundation as an extension of Aristotelean logic to cope with premises whose truth-values are uncertain, to the revisionist political coup in which the concept of probability was replaced with "statistics" (a term which originally meant "The study of surveys, censuses, and other data relevant to the state or to politics"), and the eventual rehabilitation of Laplace, Bernoulli, and Bayes' original concept of probability as a extension of logic.