On 06/11/2012 11:15 PM, Johannes Pfeifer wrote:

Could someone have a look at the lines for setting the priors for correlation in set_prior.m (occurring in at least two places):

 

    ub = [ub; max(min(estim_params_.corrx(:,5),1),-1)];

    lb = [lb; max(min(estim_params_.corrx(:,4),1),-1)];

 

In case estim_params_.corrx(:,4) is NaN, the lower bound defaults to +1 instead of -1.

Good catch!

My conjecture is it should be

 

    lb = [lb; max(min(estim_params_.corrx(:,4),-1),-1)];

 

No, this would always be -1
What about
lb = [lb; min(max(estim_params_.corrx(:,4),-1),1)];
?

Best

Michel

 

--

Johannes Pfeifer

Haußerstr. 29

72076 Tübingen

Tel.: +49-(0)7071-6396184

Mobil.: +49-(0)170-6936820

Germany

 



_______________________________________________
Dev mailing list
Dev@dynare.org
https://www.dynare.org/cgi-bin/mailman/listinfo/dev