Article ID: | iaor201523660 |
Volume: | 34 |
Issue: | 2 |
Start Page Number: | 133 |
End Page Number: | 144 |
Publication Date: | Mar 2015 |
Journal: | Journal of Forecasting |
Authors: | Hornik Kurt, Hofmarcher Paul, Crespo Cuaresma Jess, Grn Bettina |
Keywords: | simulation, forecasting: applications |
We compare the predictive ability of Bayesian methods which deal simultaneously with model uncertainty and correlated regressors in the framework of cross‐country growth regressions. In particular, we assess methods with spike and slab priors combined with different prior specifications for the slope parameters in the slab. Our results indicate that moving away from Gaussian g‐priors towards Bayesian ridge, LASSO or elastic net specifications has clear advantages for prediction when dealing with datasets of (potentially highly) correlated regressors, a pervasive characteristic of the data used hitherto in the econometric literature.