Parse error in replicating the example from user guide section 1.9

Interfaces RStan
1

Trying to replicate the example of hierarchical logistic model in section 1.9 of the user guide : 1.9 Hierarchical logistic regression | Stan User’s Guide (mc-stan.org)
A parse error appeared when I tried to compile the original example code.

data {
  int<lower=1> D;
  int<lower=0> N;
  int<lower=1> L;
  array[N] int<lower=0, upper=1> y;
  array[N] int<lower=1, upper=L> ll;
  array[N] row_vector[D] x;
}
parameters {
  array[D] real mu;
  array[D] real<lower=0> sigma;
  array[L] vector[D] beta;
}
model {
  for (d in 1:D) {
    mu[d] ~ normal(0, 100);
    for (l in 1:L) {
      beta[l, d] ~ normal(mu[d], sigma[d]);
    }
  }
  for (n in 1:N) {
    y[n] ~ bernoulli(inv_logit(x[n] * beta[ll[n]]));
  }
}

SYNTAX ERROR, MESSAGE(S) FROM PARSER:
error in ‘model1de0632d175f_test’ at line 17, column 2

15:   int<lower=0> N;
16:   int<lower=1> L;
17:   array[N] int<lower=0, upper=1> y;
     ^
18:   array[N] int<lower=1, upper=L> ll;

Here is the error message:

PARSER EXPECTED: <one of the following:
a variable declaration, beginning with type,
(int, real, vector, row_vector, matrix, unit_vector,
simplex, ordered, positive_ordered,
corr_matrix, cov_matrix,
cholesky_corr, cholesky_cov
or ‘}’ to close variable declarations>
Error in stanc(filename, allow_undefined = TRUE) :
failed to parse Stan model ‘test’ due to the above error.

If your question relates to installation please provide the following information:

  • Operating System
  • RStan Version
  • Output of writeLines(readLines(file.path(Sys.getenv("HOME"), ".R/Makevars")))
  • Output of devtools::session_info("rstan")

It seems the array declaration was not recognized. Since the model code itself was directly copied from the user guide without any change, the code should be validated. Therefore I suppose there could be something wrong with my rstan setup and configuration. I have tried diagnostics on the start guide, and uninstall and reinstall rstan but made no progress.

2

This is because the version of Stan available in RStan is unfortunately slightly outdated. Try the examples from the older version of the guide instead: 1.9 Hierarchical Logistic Regression | Stan User’s Guide

1 Like
3

Oh I completely overlooked the stan version! Thank you very much!