sugsnewclusterProb: A function to compute the probability of belonging to an...

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

Description

A function to compute the probability of belonging to an unoccupied cluster for the SUGS algorithm

Usage

sugsnewclusterProb(x, i, D, phi, betaHat, mu_0, lambda_0, nu_0, S_0)

Arguments

x	The current observation under consideration.
i	The current iteration of the SUGS algorithm
D	The number of variables
phi	The weights associated with the dirichlet grid prior
betaHat	The grid of values for the dirichlet concentration parameter
mu_0	The mean hyperparameter, default is the column means of the data matrix.
lambda_0	The variance of the Guassian mean prior, the dafault value is 0.01.
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.

Value

The unnormlised probability of the observation belonging to a new cluster

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