drugdevelopR (version 1.0.2)

Epgo_bias_binary: Expected probability to go to phase III for bias adjustment programs with binary distributed outcomes

Description

In the case we do not only want do discount for overoptimistic results in phase II when calculating the sample size in phase III, but also when deciding whether to go to phase III or not the functions Epgo_binary_L2 and Epgo_binary_R2 are necessary. The function Epgo_binary_L2 uses an additive adjustment parameter (i.e. adjust the lower bound of the one-sided confidence interval), the function Epgo_binary_R2 uses a multiplicative adjustment parameter (i.e. use estimate with a retention factor)

Usage

Epgo_binary_L2(RRgo, n2, Adj, p0, w, p11, p12, in1, in2, fixed)
Epgo_binary_R2(RRgo, n2, Adj, p0, w, p11, p12, in1, in2, fixed)

Value

The output of the functions Epgo_binary_L2 and Epgo_binary_R2 is the expected number of participants in phase III with conservative decision rule and sample size calculation.

Arguments

RRgo

threshold value for the go/no-go decision rule

n2

total sample size for phase II; must be even number

Adj

adjustment parameter

p0

assumed true rate of control group

w

weight for mixture prior distribution

p11

assumed true rate of treatment group

p12

assumed true rate of treatment group

in1

amount of information for p11 in terms of sample size

in2

amount of information for p12 in terms of sample size

fixed

choose if true treatment effects are fixed or random, if TRUE p11 is used as fixed effect

Examples

res <- Epgo_binary_L2(RRgo = 0.8, n2 = 50, Adj = 0,  p0 = 0.6,  w = 0.3,
                              p11 =  0.3, p12 = 0.5, in1 = 300, in2 = 600, 
                              fixed = FALSE)
          res <- Epgo_binary_R2(RRgo = 0.8, n2 = 50, Adj = 1,  p0 = 0.6,  w = 0.3,
                              p11 =  0.3, p12 = 0.5, in1 = 300, in2 = 600, 
                              fixed = FALSE)