I’m having some trouble getting the Mr part of a MrP model to fit efficiently with brms. I’m hoping someone may be able to help guide me toward a better fit.
Here is the R code for the model:
vote_model <- brm(mvbind(vote_trump,vote_clinton) ~ 1 + # pop level state_clinton + state_black_pct + state_hispanic_pct + state_white_protestant + # group effects (1|sex) + (1|race) + (1|age) + (1|edu) + (1|state_name) + (1|region) + # interactions b/t group effects (1|race:edu) + (1|age:edu) + (1|race:region), data = cces, family = bernoulli(link = "logit"), # stan stuff iter=1000, chains=1, cores=1, warmup=500, algorithm='sampling', save_model = 'output/stan_model_code.stan', # priors (https://github.com/stan-dev/stan/wiki/Prior-Choice-Recommendations) prior = c(set_prior("normal(0, 1)", class = "Intercept"), set_prior("student_t(3, 0, 4)", class = "sd",resp=c('votetrump','voteclinton'))), # help sampling algorithm converge (http://mc-stan.org/misc/warnings.html) control = list(adapt_delta = 0.95, max_treedepth = 10), seed = 20190605, refresh = 1)
I let it run for about 12 hours and then gave up, after which it had only completed 200 iterations. The dataset is just 40k survey respondents, so that doesn’t seem right.
R version 3.5.2 (2018-12-20) -- "Eggshell Igloo" Copyright (C) 2018 The R Foundation for Statistical Computing Platform: x86_64-apple-darwin15.6.0 (64-bit) R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. Natural language support but running in an English locale R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R.