sample.def3: using asymptotic distributions derived. considering desired...

Description Usage Arguments Value Examples

View source: R/sample.def3.R

Description

using asymptotic distributions derived. considering desired conditional assurance probability to claim overall consistency and determines optimal sample size allocation across regions by maximizing conditional assurance probability based on Definition 3 if regional treatment effects are slightly different. (Allocate equal sample size to each region if treatment effects across regions are the same.)

Usage

1
2
sample.def3(r0, alpha = 0.05, beta = 0.2, lamda, lamda_cen, L, s, u,
  eps, pai, grid = 0.1, consistency)

Arguments

r0

True overall log hazard ratio

alpha

The risk of rejecting the null hypothesis H0:r0>=0 when it is really true

beta

The risk of failing to reject the null hypothesis H0:r0>=0 when it is really false

lamda

The event hazard rate for placebo

lamda_cen

The discontinuation hazard rate

L

The whole study duration of fixed study duration design

s

Number of regions participating in the MRCT

u

A vector presents ratios of true regional log hazard ratios to true overall log hazard ratio r=u*r0

eps

Significance level of not rejecting H0 in Definition 3

pai

The preserved proportion of overall treatment effect

grid

Grid interval of the grid research

consistency

A numeric value is the desired conditional assurance probability to claim overall consistency showing only two decimal places.

Value

A list

Examples

1
2
3
set.seed(123)
Sampsize3 <- sample.def3(r0=log(0.7), alpha=0.05, beta=0.2, lamda=1, lamda_cen=1, L=2,
s=3, u=c(0.9,1,1.1), eps=0.3, pai=1/3, grid=0.1, consistency=0.8)

carolinewei/apsurvival documentation built on Nov. 4, 2019, 8:44 a.m.