Resverlogix Corp T.RVX

RE:should we hit 30% RRR or anything above 25% is good ?

[BearDownAZ]

"it is still not clear to me here which number confirm that we are successful"

The most important thing is statistical success with the primary endpoint. Statistical significance is more important than magnitude of %RRR. Typically, p-value cut-off for statistical significance is 0.05. Over is bad; under is good; way under is better. 

Also, from BETonMACE design paper:

"Statistical considerations: The apabetalone and placebo groups will be compared using a two-sided stratified log-rank test. With the assumption of 250 primary endpoint events, a 2-sided type 1 error rate of 5%, and cumulative incidence of the primary endpoint of 10.5% in the placebo arm at 18 months (4, 5, 7-9), a sample size of 2400 patients followed for a median of 18 months provides 80% power to detect a 30% relative risk reduction with apabetalone (7.47% incidence of the primary endpoint at 18 months). The protocol allowed for a possible interim analysis for futility at 75% information (188 adjudicated primary endpoints), but none was performed due to temporal proximity of this condition to the projected study end date. If superiority of apabetalone is established for the primary endpoint, a sequential gate-keeping approach will be used to control the overall Type I error rate in testing the key secondary endpoints."

So validity of secondary endpoint analysis requires the primary endpoint to acheive statistical significance (superiority). A lingering question I still don't know answer to is how the data will be received if non-significant for combined statin group but significant for the rosuvastatin arm (recall impressive synergy of apabetalone with rosuvastatin in post-hoc analysis for plaque reduction). Also, not sure how results of CKD and cognition sub-studies would be received if primary endpoint fails to achieve statistical significance.

See this post for a number of possible outcomes with the above:

https://agoracom.com/ir/Resverlogix/forums/discussion/topics/726736-betonmace-binary-outcome/messages/2231042

BDAZ