Replies to post #4356 on Dendreon Corp fka DNDNQ

[DewDiligence]

>The naive answer is 99.8% - since the false positive rate is only 0.2%<

The overwhelming majority of people who are asked give the wrong answer, and this includes practicing physicians. So it’s perhaps not surprising that most biotech investors underestimate or are unaware of program-survival bias.

(Still, most people do get it once it’s explained to them, which is why it surprises me that ocyan doesn’t.)

[ocyanblue]

Clark - Your example is a simple one in Bayesian statistics. With regard to what I say about Dew's cockamammily named "program-survival bias" thingy, what's the expression that Americans use sometimes? Yanking something or some other :). We have an expression for his type: His nose is too big, it runs.

[chebese]

<< Similarly if there are 10 worthless drugs that enter a phase ii for every one that is actually worthwhile then a p of 0.04 implies not a 4% chance that the drug is worthless, but actually much higher (I haven't specified the chance of a false negative, so I can't calculate an exact number).>>

Many thanks. Your post helps. The `bowler' example got me to think that poster DewDilligence was refering to different phenomenon altogether.

To paraphrase, I think what you are saying is that there is always a chance that stat-sig results we see in a Phase 2 trial are coming from a (truly) ineffective drug (because of limitations inherent in any trial, etc.). And therefore no one should expect positive results from the subsequent Phase 3 trial to be a shoe in even with highly stat-sig results from the Phase 2 trial.

I don't think anyone would have any trouble understanding that (if I am understanding your post correctly :-)) just as I also don't think anyone (or very few I hope) believes that 9902b has a ~95% (or some such ballpark figure based on the p value from 9901) chance of success. The current stock price and the fact we see anxiety about the pending results of 9902b suggest that people are aware of this issue (even if they are not using so many words).