rdirichlet: Generate random samples from dirichlet distribution.

In CARrampsOcl: Reparameterized and marginalized posterior sampling for conditional autoregressive models, OpenCL implementation

Description

Generate random samples from dirichlet distribution.

Usage

rdirichlet(n, parms)

Arguments

n	number of vectors to be drawn
parms	vector of parameters of dirichlet distribution

Value

n draws from the dirichlet density with parameters in parms

Author(s)

Kate Cowles

Examples

## The function is currently defined as
function (n, parms) 
{
# generate n random vectors from dirichlet
# rejection envelope

    l <- length(parms)
    x <- matrix(rgamma(l * n, parms), ncol = l, byrow = TRUE)
    sm <- x %*% rep(1, l)
    return(x/as.vector(sm))
  }

CARrampsOcl documentation built on May 2, 2019, 3:27 a.m.