endogenous priors

[pfjulio]

Hi,

Is there any "simple" way to introduce endogenous priors à lá Christiano, Trabandt and Walentin (2011) in estimation?

[jaromir-benes]

Haha, I'm pleased to inform you that the "endogenous" priors, that should correctly be called "system priors", are actually my own and my colleague Michal Andrle's invention :)) So yes, of course Iris has them, in an extremely flexible way going beyond what you find in any academic paper. So next time, please refer to them more properly :)))) You can impose priors on the following properties of the model, and you can combine any number of these: * any transformation of any point of the *autocovariance* function * any transformation of any point of the *autocorrelation* function * any transformation of any point of any kind of *shock responses* * any transformation of any point of the *power spectrum* function * any transformation of any point of the *spectral density* function * any transformation of any point of any kind of *frequency response* function * any transformation of any *eigenvalue* number See https://github.com/IRIS-Solutions-Team/Tutorial-System-Priors for some examples and a couple of slides (in the doc folder) Best Jaromir

…

On Thu, Mar 23, 2023 at 3:42 PM pfjulio ***@***.***> wrote: Hi, Is there any "simple" way to introduce endogenous priors à lá Christiano, Trabandt and Walentin (2011) in estimation? — Reply to this email directly, view it on GitHub <#369>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AGCVKKXNMQ2U7YMGFVHLFJTW5ROLPANCNFSM6AAAAAAWFJSDWM> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>