Monday, November 30, 2015

Bayesian structural equation models in JAGS: New R package by Merkle & Rosseel

blavaan: Bayesian structural equation models via parameter expansion

Edgar C. Merkle, Yves Rosseel

This article describes a novel parameter expansion approach to Bayesian structural equation model (SEM) estimation in JAGS, along with an R package implementing the approach in an open fashion. The methodology and software are intended to provide users with a general means of estimating Bayesian SEMs, both classical and novel, in a straightforward fashion. Users can estimate Bayesian versions of classical SEMs using lavaan syntax, they can obtain state-of-the-art Bayesian fit measures associated with the models, and they can export JAGS code to modify the classical SEMs as desired. This paper explains and illustrates the parameter expansion approach, and it also provides an overview and examples of package blavaan.  
Figure 2 of the article by Merkle & Rosseel.

The R package itself is here:

I have not used the package myself, but thought that many readers of this blog may be interested. If you have questions about the package please consult its creators, as I am merely announcing it.

1 comment:

  1. Thanks for posting. I've really like the lavaan package because the language is very straightforward, which makes running SEMs easy, even for people with limited R experience.

    Great to see that lavaan now includes Bayesian estimation of SEMs!