stan

The following model is model 1 of Preece and Baines (1978, Annals of Human Biology ), and is used to describe human growth. My Stan code for this model is as follows: ```{stan output.var="test"} data { int<lower=1> n; ordered[n] t; // age ordered[n] y; // height of human } parameters { positive_ordered[2] h; real<lower=0, upper=t[n-1]>theta; positive_ordered[2] s; real<lower=0>sigma; } model { h[1] ~ uniform(0, y[n]); h[2] ~ normal(180, 20); sigma ~ student_t(2, 0, 1); s[1] ~ normal(5, 5); s[2] ~ normal(5, 5); theta ~ normal(10, 5); y ~ normal(h[2] - (2*(h[2] - h[1]) * inv(exp(s[1]*(t - theta)

I am trying to get the marginal effects, according to this post: http://andrewgelman.com/2016/01/14/rstanarm-and-more/ td <- readRDS("some data") CHAINS <- 1 CORES <- 1 SEED <- 42 ITERATIONS <- 2000 MAX_TREEDEPTH <- 9 md <- td[,.(y,x1,x2)] # selection the columns i need. y is binary glm1 <- stan_glm(y~x1+x2, data = md, family = binomial(link="logit"), prior = NULL, prior_intercept = NULL, chains = CHAINS, cores = CORES, seed = SEED, iter = ITERATIONS, control=list(max_treedepth=MAX_TREEDEPTH) ) # launch_shinystan(glm1) tmp <- posterior_predict(glm1,newdata=md[,.(x1,x2)]) Issue After running

I want to graph the histograms of parameter estimates from a stan model against the priors for those parameters. I have tried doing this by running a model in stan, graphing it with ggplot2, then overlaying an approximation of the prior distribution using R's random generator function (e.g. rnorm() , rbinom() ) but I have run into many scaling issues that make the graphs impossible to get looking right. I was thinking a better way to do it would be simply to sample directly from the prior distribution and then graph those samples against the parameter estimates, but running a whole separate

I wanted to know whether it is possible to incorporate Stan in another C++ application. Since Stan is also written in C++, there should be a way. Currently, I am using RInside to achieve this but then you have all this data transferring which is time-consuming. What specifically did you want from Stan? We're going to separate out the math library into a standalone include for Stan 2.7 --- that contains all the matrix, probability, and autodiff code. Our repos already reflect this structure. All of the MCMC and transform and I/O code is callable through C++, as is the translator from a Stan