Using the wiener_lpdf() function in the cmdstanr package to implement a diffusion model ,the construction of a Markov chain was unsuccessful

Interfaces CmdStan
1

https://discourse.mc-stan.org/t/using-the-wiener-lpdf-function-in-the-cmdstanr-package-to-implement-a-diffusion-model-the-construction-of-a-markov-chain-was-unsuccessful/35213/12
I encountered the same problem as before. I ran the code with a new version of cmdstanr, but still encountered a situation where the Markov chain construction was not successful. I don’t know tChain 1 Informational Message: The current Metropolis proposal is about to be rejected because of the following issue:
Chain 1 Exception: wiener_lpdf: Inter-trial variability in A-priori bias = 0.999998, but must be smaller than 2*(A-priori bias) = 0.9 (in ‘C:/Users/admin/AppData/Local/Temp/Rtmpo5eIZw/model-c8c3ab02c4.stan’, line 28, column 8 to column 73)
Chain 1 If this warning occurs sporadically, such as for highly constrained variable types like covariance matrices, then the sampler is fine,
Chain 1 but if this warning occurs often then your model may be either severely ill-conditioned or misspecified.
Chain 1
Chain 3 Informational Message: The current Metropolis proposal is about to be rejected because of the following issue:
Chain 3 Exception: wiener_lpdf: Inter-trial variability in A-priori bias = 0.999998, but must be smaller than 2*(A-priori bias) = 0.9 (in ‘C:/Users/admin/AppData/Local/Temp/Rtmpo5eIZw/model-c8c3ab02c4.stan’, line 28, column 8 to column 73)
Chain 3 If this warning occurs sporadically, such as for highly constrained variable types like covariance matrices, then the sampler is fine,
Chain 3 but if this warning occurs often then your model may be either severely ill-conditioned or misspecified.

2

Are you still getting messages like Eigen assertion failed or Chain x finished unexpectedly?

3

Yes, it will show 1: All chains finished unexpectedly!
2: No chains finished successfully Unable to retrieve the fit

4

How far into sampling? I ran the model for ~100 iterations on each chain yesterday without issue

5

I set it up as below.Is there something wrong with my setup?
m ← mc$sample(data=stan.data,

  •            init = init.stan(),

  •            refresh = 25,

  •            iter_sampling = 1000,

  •            iter_warmup = 250,

  •            chains = chains,

  •            parallel_chains = 4,

  •            output_dir = outdir,

  •            output_basename = "fit",

  •            save_warmup = TRUE
  • )
6

It actually looks like the rc3 tar.gz file was missing some changes intended to be in it. I’m requesting new ones now, I will keep you posted.

Thanks for continuing to check our work!

7

Hi @jlb - can you try re-downloading RC3, removing any existing copy/built model, and trying again?

8

I tried deleting the old version and downloading the new version before, but still encountered an error. Perhaps it was because I didn’t delete them thoroughly. I will try again to see if the same problem will occur again. Thank you for your help.