****  Stata do file for cluster-randomized study of nutritional interventions in Kenyan Schools **********

/*

See http://www.gllamm.org/bayes.html

Reference:
Chung, Y., Rabe-Hesketh, S., Dorie, V., Gelman A. and Liu, J. (2013).
A nondegenerate penalized likelihood estimator for variance parameters
in multilevel models. Psychometrika 78, 685-709.

*/

* Install software (if needed)
ssc install gllamm, replace  
* download init_prior and calc_prior from http://www.gllamm.org/bayes.html

* Load data from "Multilevel and Longitudinal Modeling Using Stata"
use http://www.stata-press.com/data/mlmus3/kenya, clear

* MLE
xtset schoolid

tab treatment, generate(treat)
rename treat1 meat
rename treat2 milk
rename treat3 calorie

xtreg ravens meat milk calorie age_at_time0 if rn==5, mle

* MPL
gllamm ravens meat milk calorie age_at_time0 if rn==5, ///
   i(schoolid) adapt prior(gamma, scale(10000) shape(2))

*check quadrature number of points
gllamm ravens meat milk calorie age_at_time0 if rn==5, ///
   i(schoolid) adapt prior(gamma, scale(10000) shape(2)) nip(20)