Truncated Prior for normal distribution

Estimation ML/Bayesian estimation
1

Hi everyone,
Can someone tell me to draw a truncated prior?
I want to write the prior for parameter Xini, with mean = -1 and std error = 0.1, normal distribution, but Xini can have only negative values.
Is prior code like below correct?
Xini, -1, -inf, 0, normal_pdf,-1, 0.1;
Thanks in advance…

2

For the moment, Dynare does not support truncated priors except during mode-finding. Do you use a steady state file?

3

Thank you!
Yes, I use a steady state file.

4

In that case, it is easiest to implement the truncation in that file. Check whether the bound is satisfied and if not, set the error code and return:

if Xini>0 % parameter violates restriction
    params=M_.params;
    check=1; %set failure indicator
    return; %return without updating steady states
end