TrialSize (version 1.4)

TwoSampleSurvival.NIS: Test for two sample Non-Inferiority/Superiority in exponential model for survival data

Description

margin=lamda1-lamda2, the true difference of hazard rates between control group lamda1 and a test drug group lamda2

H0: margin <= delta

Ha: margin > delta

if delta >0, the rejection of Null Hypothesis indicates the superiority of the test drug over the control;

if delta <0, the rejection of the null hypothesis implies the non-inferiority of the test test drug against the control.

Usage

TwoSampleSurvival.NIS(alpha, beta, lam1, lam2, k, ttotal, taccrual, gamma,margin)

Arguments

alpha

significance level

beta

power = 1-beta

lam1

the hazard rates of control group

lam2

the hazard rates of a test drug

k

k=n1/n2 sample size ratio

ttotal

Total trial time

taccrual

accrual time period

gamma

parameter for exponential distribution. Assume Uniform patient entry if gamma =0

margin

margin=lamda1-lamda2, the true difference of hazard rates between control group lamda1 and a test drug group lamda2

References

Chow SC, Shao J, Wang H. Sample Size Calculation in Clinical Research. New York: Marcel Dekker, 2003

Examples

# NOT RUN {
Example.7.2.4<-TwoSampleSurvival.NIS(0.05,0.2,1,2,1,3,1,0.00001,0.2)
Example.7.2.4

# }