PerMallows (version 1.13)

dgmm: Calculate the probability of a permutation in a GMM

Description

Calculate the probability of a permutation sigma in a GMM of center sigma0, dispersion parameter theta and under the specified distance

Usage

dgmm(perm, sigma0 = identity.permutation(length(perm)), theta,
  dist.name = "kendall")

Arguments

perm

permutation whose probability wants to be known

sigma0

central permuation of the GMM, by default the identity

theta

vector dispersion parameter of the GMM

dist.name

optional name of the distance used in the GMM. One of: kendall (default), cayley, hamming

Value

The probability of sigma in the given GMM

Examples

data <- matrix(c(1,2,3,4, 1,4,3,2, 1,2,4,3), nrow = 3, ncol = 4, byrow = TRUE)
sig <- c(1,2,3,4)
th <- c(0.1, 0.2, 0.3,1)
log.prob <- apply(data,MARGIN=1,FUN=function(x){log(dgmm(x,sig, th, "hamming"))})
sum(log.prob)
dgmm (c(1,2,3,4), theta=c(1,1,1))
dgmm (c(1,2,3,4), theta=c(1,1,1), dist.name="cayley")