|
Activity Number:
|
497
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 10, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #306900 |
|
Title:
|
Leveling the Playing Field: Prior Choice and DSGE Model Comparisons
|
|
Author(s):
|
Marco Del Negro*+
|
|
Companies:
|
Federal Reserve Bank of Atlanta
|
|
Address:
|
1000 Peachtree Street, Atlanta, GA, 30309,
|
|
Keywords:
|
Bayesian analysis ; DSGE models
|
|
Abstract:
|
What frictions are important in a DSGE model? In the Bayesian DSGE literature (e.g., Smets and Wouters 2003), this question is answered by computing the posterior odds of the model with and without the friction of interest. The prior distribution for the deep parameters plays a key role in these model comparisons. For some parameters, such as the autocorrelations and standard deviations of the structural shocks, the choice of the prior is not straightforward and can make a difference for model comparison. We provide an approach for choosing the prior that is aimed at leveling the playing field for DSGE model comparisons.
|
