Clearing The Air

Thursday, April 12, 2007

As a society should we support the use of fraudulent science in order to arrive at a desired agenda?

Walter E. Williams writes:

The EPA claimed that 3,000 Americans die annually from secondhand smoke, but there was a problem. They couldn’t come up with that conclusion using the standard statistical 95 percent confidence interval. They lowered their study’s confidence interval to 90 percent. That has the effect of doubling the margin of error and doubling the probability that mere chance explains those 3,000 deaths.

The Congressional Research Service said, “Admittedly, it is unusual to return to a study after the fact, lower the required significance level, and declare its results to be supportive rather than unsupportive of the effect one’s theory suggests should be present.” The CRS was being kind. This kind of doctoring of research results would get a graduate student expelled from a university.

In 1998, the World Health Organization’s International Agency for Research on Cancer released the largest-ever and best-formulated study on ETS. The research project ran for 10 years and in seven European countries. The study, not widely publicized, concluded that no statistically significant risk existed for nonsmokers who either lived or worked with smokers.

During the late `90s, at a Washington affair, I had the occasion to be in the presence of an FDA official. I asked him whether he would approve of pharmaceutical companies employing EPA’s statistical techniques in their testing of drug effectiveness and safety. He answered no. I ask my fellow Americans who are nonsmokers: Do you support the use of fraudulent science in your efforts to eliminate tobacco smoke nuisance in bars, restaurants, workplaces and hotels?

You say, “Okay, Williams, the science is bogus, but how do we nonsmokers cope with the nuisance of tobacco smoke?” My answer is that it all depends on whether you prefer liberty-oriented solutions to problems or those that are more tyranny-oriented.

Which leads me to ask the obvious question:

Or should society use science to test a hypothesis......and then report the facts.......whether the results support the agenda or not?

I submit to you that the latter method is the proper manner to implement public policy.

It is clear that the pro-smoking ban lobby is not interested in facts nor science........I would however, hope that lawmakers would show some interest in the proper manner and role of science to determine public policy......it doesn't look good though.