We investigate the issue of model uncertainty in cross-country growth regre
ssions using Bayesian Model Averaging (BMA). We find that the posterior pro
bability is spread widely among many models, suggesting the superiority of
BMA over choosing any single model. Out-of-sample predictive results suppor
t this claim. In contrast to Levine and Renelt (1992), our results broadly
support the more 'optimistic' conclusion of Salai-Martin (1997b), namely th
at some variables are important regressors for explaining cross-country gro
wth patterns. However, care should be taken in the methodology employed. Th
e approach proposed here is firmly grounded in statistical theory and immed
iately leads to posterior and predictive inference. Copyright (C) 2001 John
Wiley & Sons, Ltd.