This is in response to my post that I agree generally that most DSMBs allow even very low p values to go to the end. Not halt unless there is an interim. So I think we're mostly in agreement. ? (And note this more conservative view of mine is a shift from my earlier view, and was caused by the discussion in this thread. So thanks.)
FWIW I think our only disagreement is that I am less absolutist? But that is based upon the fact that I've read a ton of statistical reviews, papers, ... and have bumped into more than one unplanned halt. But I've never made a study of them (e.g. Categorized them by NDA vs SNDA vs number of zeros in the p value vs whether the endpoint was OS or some lesser thing, ...)
Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.