No Stata code this week because of the Easter break, so I thought that I would take the opportunity to trail a couple of the topics that I will be covering over the coming months.
It is unusal for me to plan ahead in this way but I have been investigating a Bayesian analysis program called Stan (http://mc-stan.org/) both to assess its performance in comparison with WinBUGS and to see how easy it is to control from within Stata. It turns out that Stan works well and it is very easy to integrate Stan with Stata so I will use this blog to describe the program and to show how a Stata user can access it.
Before I get to Stan, I need to finish my analysis of the Poisson regression problem. I still have to describe my Mata program for data augmentation and I want to describe how a Stata user can access the R package glmmMCMC to fit a Poisson mixed model.
In the long-term I have only the vaguest of ideas. Having access to Stan will enable me to look at much more complex Bayesian models but I am concerned to ensure that I also cover more straightforward applications. Perhaps I’ll discuss Bayesian meta-analysis or maybe Bayesian experimental design.
I would be very pleased to receive suggestions if anyone has a special type of Bayesian model that they want to fit with Stata.
Happy Easter
Subscribe to John's posts
Comments are closed, but trackbacks and pingbacks are open.