<b>ParMA</b>: Parallelized Bayesian Model Averaging for Generalized Linear Models

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