I need to calculate the necessary sample size to proof non-inferiority with censored data. I found out a SUGI paper titled: "Design and analysis of equivalence clinical trials via the SAS system" by Pamela et al.
In this paper, the authors use the following equation:
m = 4(Z(1-alfa)+Z(1-beta))^2 / ln(delta)^2
Z(x) is the inverse normal standard distribution and delta is the non-
This equation is telling us that the sample size for a non-inferiority
test with survival data depends only of the non-inferiority range.
Therefore, the sample size is independent to the observed Hazard Rate
or possible deviations, parameters which are very important in other
non-inferiority tests as for example non-inferiority for two means. No
matter if my experimental drug is usually superior to the active
control, the only parameter that affects the selection of the sample
size is the non-inferiority range!!
Does somebody know if these interpretations are correct? I think that
it is a hard affirmation and I would to be confident before do it.
Thanks in advance.
Juan Vicente Torres.