Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Pastimes : Let's Talk About Our Feelings!!! -- Ignore unavailable to you. Want to Upgrade?

To: Ilaine who wrote (41381)	6/21/1999 6:49:00 PM
From: The Philosopher	Respond to of 108807

Excellent find. Thanks for taking the time to root this out and post it.

To: Ilaine who wrote (41381)	6/21/1999 8:19:00 PM
From: Chuzzlewit	Respond to of 108807

Blue, thanks for the link. I was not aware of the problems with these studies. It was quite interesting, but it illustrates a point I made some time ago. Theories must fit observations, not the other way round. Science is replete with similar examples to the one you referenced, but notice that the observations remain intact. Explanations, however, must yield to observed fact. We are still left with the problem of rapid industrial melanization. This is either the result of a yet to be discovered adaptive advantage of one form over the other, or it is the result of a non-adaptive mechanism. The interpretation must await further investigation. I would not characterize the data as doctored, so much as the conclusion hastily drawn. And this underscores the reason for continually retesting our ideas. One part of the article is clearly wrong: "Instead of viewing experiments as a way to prove or disprove an idea, we should come to see them as a way of interacting with phenomena." The whole idea of an experiment is to disprove an hypothesis. This frequently takes the form of testing the null hypothesis. For example, suppose there were a drug designed to ameliorate arthritic pain. An experiment would be designed to specifically test the hypothesis that the drug exerted no effect. The results of the experiment would be subjected to statistical tests to determine whether the null hypothesis should be rejected. But the experimental setting itself is part of the set of variables. That's why placebos and double blind designs are used. TTFN, CTC