Biotech Valuation Message Board

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 : Biotech Valuation

CRSP 52.08

+1.9%

1:41 PM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Biomaven who wrote (2541)	1/11/2001 9:39:00 PM
From: Spekulatius	Read Replies (2) of 52153

Regarding the CVTX trial - I have to admit that I am not familiar with the details but it sounds like the following things has happened: CVTX trial designer came up with the enrollment numbers for each arm based on an estimate of the treadmill time standardeviations within each group and an estimate of the difference of treadmill time between the placebo and the group taking the drug. These estimates were supposedly taken from earlier trials (PhII). With these date, the trial designer can calculate the number of participants (n) needed to get a statistical significant result (p<0.05). However, when one or both standardeviations for the placebo/drug group is bigger than expected, this may not work and the study will not show a statistical significant result. So one thing the trial designer can do, is to throw in more participants; this however, does not work too well,since double the number of participants (N) would increase the 'resolution' of the trial only by sqrt(n); it will work only for a narrow miss. The other problem is that this of course does reduce the cleanliness of the trial since its sort of trying again and again, so hopefully this has been signed off by the FDA. I guess by looking into the data one could make an estimate of CVTX explanation makes sense...

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next