Dynare causing Matlab/Octave to crash
Posted: Fri Mar 21, 2014 1:23 pm
Hi all,
I'd be grateful for any help on this problem as I'm unable to solve it and I haven't found a solution on the forum.
I'm trying to estimate a model with five mcmc chains and with mh_replic = 100,000. I have tried this on a desktop (Windows 8, Octave 3.6.4 and Dynare 4.4.2) and on the university Linux-based network (Matlab R2013a, Dynare 4.4.1) and the sofrware always crashes. With Octave I get the message
Estimation:: mcmc: Write details about the MCMC... Ok!
Estimation::mcmc: Details about the MCMC are available in ...
terminate called after throwing an instance of 'octave_execution_exception'
This application has requested the Runtime to terminate it in an unusual way.
Please contact the application's support team for more information.
panic: Aborted -- stopping myself...
With Matlab on the network it just goes off (as it's not installed on my office computer) so I do not get to see the error message. However, it occurs after about 60% of the acceptance rate calculations with the second MCMC chain.
What's puzzling is that if I keep the number of mh_replic lower, say 20,000, it works fine so I don't think there's anything wrong with the .mod file or the data.
If it's any help, I'm attaching the mod file and the zip file contains the data I used as well as the Matlab crash information file.
Any help would be really appreciated
I'd be grateful for any help on this problem as I'm unable to solve it and I haven't found a solution on the forum.
I'm trying to estimate a model with five mcmc chains and with mh_replic = 100,000. I have tried this on a desktop (Windows 8, Octave 3.6.4 and Dynare 4.4.2) and on the university Linux-based network (Matlab R2013a, Dynare 4.4.1) and the sofrware always crashes. With Octave I get the message
Estimation:: mcmc: Write details about the MCMC... Ok!
Estimation::mcmc: Details about the MCMC are available in ...
terminate called after throwing an instance of 'octave_execution_exception'
This application has requested the Runtime to terminate it in an unusual way.
Please contact the application's support team for more information.
panic: Aborted -- stopping myself...
With Matlab on the network it just goes off (as it's not installed on my office computer) so I do not get to see the error message. However, it occurs after about 60% of the acceptance rate calculations with the second MCMC chain.
What's puzzling is that if I keep the number of mh_replic lower, say 20,000, it works fine so I don't think there's anything wrong with the .mod file or the data.
If it's any help, I'm attaching the mod file and the zip file contains the data I used as well as the Matlab crash information file.
Any help would be really appreciated