Wall and others--
Can you statistics knowledgeable guys answer one for me?
As I understand the current situation with the interim analysis of Provenge the interim will occur when there are 180 deaths in the study. As Gold has recently emphasized in both the CC and the presentation at the conference this is greater than the number of deaths in the pooled 9901 and 9902a sample. The pooled sample turned out to have a p value of .01 did it not (maybe it was .011?)? And also the interim has prespecified that the same Cox regression analysis will be performed as that which resulted in a corrected p value for the pooled data of .002. I know there are differences in the patient populations based on the previous tinkering with the study--first Gleason scores less than 7 based on earlier inkling that that group did best in 9901, then amended to include all Gleason scores and "minimal symptoms"--but again Gold has said that an analysis of the populations finds them to be "similar" for study purposes. I also know that "most interim analyses do not attain statistical significance" as has been quoted ad nauseum in the press when discussing the interim.
My question is this--If we have drunk the Kool aid and really believe Provenge works as the explanation for the results of 9901 and pooled data of 9901 and 9902a, why should we not believe that the interim--with more patients and more death events than the pooled groups--will be stat sig--and even gloriously stat sig after Cox? Am I missing something? Do we need to wait for 3 year survival to expect the best possible results? Is there something about "curve separation" (which has never been explained to me by the way and I don't really understand--I'd appreciate an explanation)?
Please enlighten me, if you can. Seems like if there are 180 deaths--and again the vast majority are placebo guys, the interim should look as good as the pooled data did.
News 
Market Data 
Discover 
