How to determine priors?


#1

Hello People, I have developed a model with many new kind of frictions. Due to lack of literature available currently, i just want a general guidance on how to determine the priors of persistence and standard devaition of these new shocks?

Thank you


#2

Please see the discussion at


#3

Thank you Professor!!!


#4

Hey, I am using 13 observed variables. For each observed variable, I have 24 observations at annual frequency. I have used one-sided HP filter on my data.

Total number of structural shocks are 10. In addition to it, I have included measurement errors as well.

Just want to know, Is it OK, what I am doing?


#5

Just based on your description, there is nothing here that is immediately wrong.


#6

I wonder if the length of time series is sufficient to produce credible results?


#7

This is not a concept applicable for a Bayesian. If the sample is short or the data informative, your prior will not be updated by much. But that is perfectly fine. You just need to openly communicate this.