Working Paper: CEPR ID: DP10590
Authors: James Rockey; Jonathan Temple
Abstract: The issue of model uncertainty is central to the empirical study of economic growth. Many recent papers use Bayesian Model Averaging to address model uncertainty, but Ciccone and Jarocinski (2010) have questioned the approach on theoretical and empirical grounds. They argue that a standard 'agnostic' approach is too sensitive to small changes in the dependent variable, such as those associated with different vintages of the Penn World Table (PWT). This paper revisits their theoretical arguments and empirical illustration, drawing on more recent vintages of the PWT, and introducing an approach that limits the degree of agnosticism.
Keywords: Bayesian model averaging; growth econometrics; growth regressions
JEL Codes: C51; O40; O47
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| initial GDP per capita (E20) | posterior inclusion probabilities (C11) |
| regional dummies (R15) | posterior inclusion probabilities (C11) |
| initial GDP per capita and regional dummies (R15) | growth determinants (O41) |
| model uncertainty (D80) | false positives (C52) |
| restricting model space (C24) | stability and robustness (C62) |