In the paper A general inefficacy interim monitoring rule for randomized clinical trials, they propose boundaries for interim analyses using the hazard ratios. These boundaries are illustrated in an example aiming to test H0: HR = 1 vs H1: HR = 0.75. They show the boundaries in the hazard ratio scale and Z-value scale as below:

enter image description here

How can we transform from hazard ratio scale to Z-value scale?

  • $\begingroup$ Hazard ratios are more useful metrics for understanding the stopping boundary. But you can convert between the two. I believe an R package for group sequential testing does this. $\endgroup$ Commented Jul 11 at 11:56


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.