I’m trying to specify the joint distribution of 3 parameters in JAGS using a truncated multivariate normal (one of the 3 parameters is truncated at zero, the others are untruncated).

I’ve successfully implemented the 1 parameter case using:

a ~ dnorm(mu,prec)T(0, )

And a bivariate case using the trick discussed here: https://sourceforge.net/p/mcmc-jags/discussion/610037/thread/9472caff/

But I am stuck on the extension to 3 parameters. Any suggestions would be greatly appreciated!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.