Dynare forums

I have been trying to reproduce the estimated results in Justiniano and Preston (2010).
In this paper, the priors for the standard deviations of the shocks are chosen as

"Inverse-Gamma 1 densities with infinite variance by fixing the degrees of freedom at 2.
The scale parameters are chosen to obtain a mean of 0.5"

However, in dynare, we can only specify means (p(1)) and standard deviations (p(2)) when imposing priors that follow inverse gamma distribution.

For example,

Code: Select all

estimated_params ;

...
...
stderr eps_z, , , , INV_GAMMA_PED, p(1), p(2)

end;


Is there any way to specify p(1) and p(2) in this case?

Sorry, but at the current stage, we only support distributions with finite moments, see https://github.com/DynareTeam/dynare/issues/846
Try using a large variance instead. This should not make a difference.