Closed jgslazzaro closed 1 week ago
Thanks for the reprex, I'll look into this next year; I don't see anything obviously wrong in your code, so I need to run valgrind to check for memory leaks.
Ok, solved the issue: You are defining P1
as 2x2 matrix with every element as 10, which is not a valid covariance matrix. This leads to failure of the cholesky decomposition in state simulation, and for some reason on windows this crashes R instead of throwing an error (as it does if you run sim_smoother(mod)
). Setting P1 <- diag(10, m)
should fix the model and allow the MCMC to run without issues.
Hi, I am trying to estimate a multivariate linear gaussian model. However, R crashes whenever I call the run_mcmc function. A toy example with simulated data is below.
The only output I get is the progress bar and after completion Rstudio tells me that the R Session aborted without further explanation.
Kalman filtering works fine.
Session Info
```r ```