compMlvarsel: Computes the log marginal likelihood of clustering and...

In ococrook/sugsvarsel: SUGS algorithm of Wang and Dunson (2011), SUGS VarSel algorithm Crook et al.

Description

Computes the log marginal likelihood of clustering and variable selection

Usage

compMlvarsel(K, D, n, nu_0, S_0, lambda_0, nu, lambda, S, lognullMarg,
  intfeature)

Arguments

K	The number of currently occupied clusters
D	The number of variable in the data matrix.
n	The vector indicating the number of observations in each cluster
nu_0	The degrees of freedom hyperparameter, the default value is D, where D is the number of variables.
S_0	The scale hyperparamter, the deault value is a fifth of the column variance of the data matrix.
lambda_0	The variance of the Guassian mean prior, the dafault value is 0.01.
nu	The current posterior degrees of freedom
lambda	The current posterior mean variance
S	The current posterior scale vector
lognullMarg	The log marginal probability of a variable belonging to the null model
intfeature	A binary vector of feature which are parition as irrelevant (0) or relevant (1).

Value

The log marginal likelhood

ococrook/sugsvarsel documentation built on May 27, 2019, 12:12 p.m.