pmvnorm_combo: Multivariate Normal Distribution for Multivariate Maximum...

In keaven/gsDesign2: Group Sequential Design with Non-Constant Effect

Multivariate Normal Distribution for Multivariate Maximum Statistics

Description

Computes the distribution function of the multivariate normal distribution with maximum statistics for arbitrary limits and correlation matrices

Usage

pmvnorm_combo(
  lower,
  upper,
  group,
  mean,
  corr,
  algorithm = GenzBretz(maxpts = 1e+05, abseps = 1e-05),
  ...
)

Arguments

lower	the vector of lower limits of length n.
upper	the vector of upper limits of length n.
group	the vector of test statistics group.
mean	the mean vector of length n.
corr	the correlation matrix of dimension n.
algorithm	an object of class GenzBretz, Miwa or TVPACK specifying both the algorithm to be used as well as the associated hyper parameters.
...	additional parameters transfer to mvtnorm::pmvnorm

Details

Let $Z = Z_ij$ be a multivariate normal distribution. Here i is a group indicator and j is a within group statistics indicator. Let G_i = max(Z_ij) for all test within one group. This program are calculating the probability

$$Pr( lower < max(G) < upper )$$

keaven/gsDesign2 documentation built on Oct. 13, 2022, 8:42 p.m.