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.

Biotech / Medical : XOMA. Bull or Bear? -- Ignore unavailable to you. Want to Upgrade?

To: Robert K. who wrote (8622)	2/4/1999 10:38:00 AM
From: Robert K.	Respond to of 17367

Oh,Oh,Oh........and what form might that combination take?>>>>>>> >>>>>http://www.ncbi.nlm.nih.gov/htbin-post/Entrez/query?uid=9919353&form=6&db=m&Dopt=b

To: Robert K. who wrote (8622)	2/4/1999 3:01:00 PM
From: Cacaito	Read Replies (1) \| Respond to of 17367

Robert K. I was responding to two different questions from Gwohanka: 1. 95% confidence level is the reverse (but the same)of the P <0.05, this means that there is 1 in 20 chances (Statistics is based on chances) that an effect is due to the drug (or intervention)and not to chance. If you flip a coin you have two probabilities, either side A, or B. It could happen that you will get 10 times the side A and concluded that you will go to bet on your strong ability to get the side A. Well do bet your money on it for a long time, because the more times one flips the more chances that the results will even to 50% chances. The FDA wants to make sure that the results are due to the drug and not to chances. Scientists kind of agree that if one gets the expected result 19 out of 20 times then one should go a bet in Vegas with it. But to determine this in complex diseases with multiple interactions not control by the investigators it gets complicated to formulas in order to establish a fact. To the disbelief of many, this formulas save time and money and clinical trials shorter with much less number of patients than simple flipping. Plus, because of the smaller number of patients the variables to control are less (not more). 2. Then I gave George an example of real life Medicine. He considers a 50% chance to intervene with a (probably not needed)drug a low risk, Well in many procedures physicians are working with a less than 5% chance of the drug being needed due to the uncertainties of diagnosis. So 1 patient is help when 20 are treated (19 did not need the drug).