# Error codes from rstan::optimizing

I have a fairly simple model on which rstan::optimizing often fails with an error code of 70. What, specifically, does this code indicate? It’s hard to figure out how to address the problem without having any idea why the optimization is failing.

The model is basically this:

\mu_t = a + b \cdot t
a_t \sim \mbox{AR(1) process}
y_t = \mu_t + a_t \cdot \mu_t ^ x

All of x, a, b, and the AR(1) parameters are being estimated, with x restricted to the interval (0,1) and the autoregressive coefficient \phi restricted to (0,1). The parameterization used is a, b, \mathrm{logit}(\phi), \mathrm{logit}(x), and \log(\sigma_{\epsilon} \cdot \mu_u^x), where u is the midpoint of the time series.

Does it come from Stan or from R when it tries to do the Hessian via optimHess? I don’t think we have an error code of 70

I’m not asking for the Hessian when I cal rstan::optimizing, so I don’t think optimHess would be involved.