Replies to post #1138 on Dendreon Corp fka DNDNQ

[Gametheory101]

Wouldn't you have to mathematically account for a 2 to 1 randomization to reach assuredness of being at the median before unblindnig?

Realistically, the number could be less than 146 with a 99% or 98% level of confidence, but how much less?

Maybe we could get a little help from our stats folks.