random_start: Appropriate simulation of starting values for tandom...

In PLMIX: Bayesian Analysis of Finite Mixture of Plackett-Luce Models

Appropriate simulation of starting values for tandom initialization of Gibbs Sampling. It start from the mle corresponding to no-group structure and then it randomly selects rescaled random support points (with sum 1) of G mixture components such that the marginal support coincides with the mle support for G=1 Random generation of starting values of the component-specific support parameters for Gibbs sampling

Description

Appropriate simulation of starting values for tandom initialization of Gibbs Sampling. It start from the mle corresponding to no-group structure and then it randomly selects rescaled random support points (with sum 1) of G mixture components such that the marginal support coincides with the mle support for G=1 Random generation of starting values of the component-specific support parameters for Gibbs sampling

Usage

random_start(mlesupp, givenweights, alpha = rep(1, G))

Arguments

mlesupp	MLE of support parameters
givenweights	A numeric vector of G mixture weights
alpha	A numeric vector of G positive reals to be used as Dirichlet parameters for the random start which corresponds to a convex combination of G support parameter vertices

Value

out A numeric G\timesK matrix with starting values of the component-specific support parameters

Author(s)

Cristina Mollica and Luca Tardella

PLMIX documentation built on July 1, 2025, 1:12 a.m.