Choosing Prior Hyperparameters

Bayesian inference is common in models with many parameters, such as large VAR models, models with time-varying parameters, or large DSGE models. A common practice is to focus on prior distributions that themselves depend on relatively few hyperparameters. The choice of these hyperparameters is cruc...

Full description

Saved in:
Bibliographic Details
Published inFederal Reserve Bank of Richmond. Working Paper Series Vol. 16; no. 9; p. 1
Main Authors Amir-Ahmadi, Pooyan, Matthes, Christian, Wang, Mu-Chun
Format Web Resource
LanguageEnglish
Published Richmond Federal Reserve Bank of Richmond 01.08.2016
Subjects
Algorithms
Bayesian analysis
Economic models
Researchers
Time series
Volatility
United States > US
Minnesota
Online AccessGet full text

Cover

More Information
Summary:Bayesian inference is common in models with many parameters, such as large VAR models, models with time-varying parameters, or large DSGE models. A common practice is to focus on prior distributions that themselves depend on relatively few hyperparameters. The choice of these hyperparameters is crucial because their influence is often sizeable for standard sample sizes. In this paper we treat the hyperparameters as part of a hierarchical model and propose a fast, tractable, easy-to-implement, and fully Bayesian approach to estimate those hyperparameters jointly with all other parameters in the model. In terms of applications, we show via Monte Carlo simulations that in time series models with time-varying parameters and stochastic volatility, our approach can drastically improve on using fixed hyperparameters previously proposed in the literature.
Bibliography:SourceType-Other Sources-1
content type line 65
ObjectType-Feature-1