Replies to post #1356 on Dendreon Corp fka DNDNQ

[iwfal]

it is very likely that they already have the ellapse times of the median and 75% percentile for the placebo population. The difference between these gives a reasonable estimate of the median PSAR.

In a continuous enrollment situation (vs instantaneous spike enrollment), I am not sure how you can calculate PSAR at all exactly based upon the cumulative number of events. Yep, you can put bounds on the median PSAR ... but pretty inexact since the data has been put through an integrating filter.