ParMA: Parallelized Bayesian Model Averaging for Generalized Linear Models

Riccardo Lucchetti

doi:10.18637/jss.v104.i02

ParMA: Parallelized Bayesian Model Averaging for Generalized Linear Models

2022-01-01

2

OA

AI

DOI：10.18637/jss.v104.i02

Original

Original request for help

Save

Abstract

En 中文

This paper describes the gretl function package ParMA, which provides Bayesian model averaging (BMA) in generalized linear models. In order to overcome the lack of analytical specification for many of the models covered, the package features an im-plementation of the reversible jump Markov chain Monte Carlo technique, following the original idea by Green (1995), as a flexible tool to model several specifications. Particular attention is devoted to computational aspects such as the automatization of the model building procedure and the parallelization of the sampling scheme.

Keywords:

BMA

GLM

RJMCMC

parallelization

gretl

ParMA: Parallelized Bayesian Model Averaging for Generalized Linear Models

Abstract

Journal

Organization

Cited Papers