Vlad Kogan writes:
I’ve using your book on regression and multilevel modeling and have a quick R question for you. Do you happen to know if there is any R package that can estimate a two-stage (instrumental variable) multi-level model?
My reply: I don’t know. I’ll post on blog and maybe there will be a response. You could also try the R help list.
Vlad, I am currently fitting some two-stage multilevel models using Bugs as called from R, following the guidance of Gelman and Hill pg. 509-511. Since you say you are using this same book, is there a reason you don't want to fit the model in Bugs?
I noticed some minor typos in the Bugs code on pages 510 and 511 (Sigma.ag is later referred to just as Sigma, for instance), but after correcting these and altering some things to fit my particular problem, the code has worked well for me.
The bayesm package includes some functions for Bayesian instrumental variables with different models of unit heterogeneity, including normal, normal mixtures, and mixtures of Dirichlet processes.
Conley, T. G., Hansen, C. B., McCulloch, R. E., & Rossi, P. E. (2008). A semi-parametric Bayesian approach to the instrumental variable problem. Journal of Econometrics, 144(1), 276-305. doi:10.1016/j.jeconom.2008.01.007