Default Priors and Predictive Performance in Bayesian Model Averaging, with Application to Growth Determinants
31 Pages Posted: 8 May 2012
Date Written: April 3, 2009
Abstract
Bayesian model averaging (BMA) has become widely accepted as a way of accounting for model uncertainty, notably in regression models for identifying the determinants of economic growth. To implement BMA the user must specify a prior distribution in two parts: a prior for the regression parameters and a prior over the model space. Here we address the issue of which default prior to use for BMA in linear regression. We compare 12 candidate parameter priors: the Unit Information Prior (UIP) corresponding to the BIC or Schwarz approximation to the integrated likelihood, a proper data-dependent prior, and 10 priors considered by Fernandez et al. (2001b). We also compare the uniform model prior to others that favor smaller models. We compare them on the basis of crossvalidated predictive performance on a well-known growth dataset and on two simulated examples from the literature. We found that the UIP with uniform model prior generally outperformed the other priors considered. It also identified the largest set of growth determinants.
Keywords: Growth Determinants, Model Uncertainty, Bayesian Model Averaging (BMA), Parameter and Model Prior Elicitation, Predictive Performance
JEL Classification: O51, O52, O53
Suggested Citation: Suggested Citation
Do you have negative results from your research you’d like to share?
Recommended Papers
-
By Eduardo Ley and Mark F.j. Steel
-
By Eduardo Ley and Mark F.j. Steel
-
Are Any Growth Theories Robust?
By Steven N. Durlauf, Andros Kourtellos, ...
-
Jointness of Growth Determinants
By Gernot Doppelhofer and Melvyn Weeks
-
Determinants of Economic Growth: Will Data Tell?
By Antonio Ciccone and Marek Jarocinski
-
Determinants of Economic Growth: Will Data Tell?
By Antonio Ciccone and Marek Jarocinski
-
Growth Empirics Under Model Uncertainty: Is Africa Different?
-
Jointness in Bayesian Variable Selection with Applications to Growth Regression
By Eduardo Ley and Mark F.j. Steel
-
Jointness in Bayesian Variable Selection With Applications to Growth Regression
By Eduardo Ley and Mark F.j. Steel