PBE {TrialSize} | R Documentation |
Consider 2 by 2 crossover design.
H0: lamda >= 0
Ha: lamda < 0
PBE(alpha, beta, sigma1.1, sigmatt, sigmatr, sigmabt, sigmabr, rho, a, delta, lamda)
alpha |
significance level |
beta |
power = 1-beta |
sigma1.1 |
σ_{a.b}^2=σ_{D}^2+aσ_{WT}^2+bσ_{WR}^2. Here a=b=1. |
sigmatt |
σ_{tt}^2=σ_{BT}^2+σ_{WT}^2, σ_{wt}^2 is the within-subjects variance in test formulation |
sigmatr |
σ_{tr}^2=σ_{BR}^2+σ_{WR}^2, σ_{wr}^2 is the within-subjects variance in reference formulation |
sigmabt |
σ_{bt}^2 is the between-subjects variance in test formulation |
sigmabr |
σ_{br}^2 is the between-subjects variance in reference formulation |
rho |
rho is the inter-subject correlation coefficient. |
a |
a= thetaPBE =1.74 |
delta |
delta is the mean difference of AUC |
lamda |
lamda=delta^{2}+σ^2-σ_{TR}^2-thetaPBE*max(σ_{0}^2,σ_{TR}^2) |
Chow SC, Shao J, Wang H. Sample Size Calculation in Clinical Research. New York: Marcel Dekker, 2003
Example.10.3<-PBE(0.05,0.2,0.2,sqrt(0.17),sqrt(0.17),0.4,0.4,0.75,1.74,0.00,-0.2966) Example.10.3 # 12