This paper examines the robustness of explanatory variables in cross-country economic growth regressions using a novel Bayesian Averaging of Classical Estimates (BACE) approach. The authors find that 11 variables are robustly partially correlated with long-term growth, while five are marginally related. The strongest evidence is for the initial level of real GDP per capita. The BACE method combines Bayesian model averaging with classical OLS estimation, using weights proportional to the likelihoods of each model. This approach allows for a more accurate estimation of variable importance in growth regressions by accounting for model uncertainty. The results show that variables with high inclusion probabilities are robustly related to growth, while others are only marginally related. The paper concludes that the data support the hypothesis that there is a set of variables robustly partially correlated with economic growth, contradicting the extreme bounds test which would reject the significance of every single variable. The BACE method provides a more nuanced understanding of variable importance in growth regressions compared to traditional methods.This paper examines the robustness of explanatory variables in cross-country economic growth regressions using a novel Bayesian Averaging of Classical Estimates (BACE) approach. The authors find that 11 variables are robustly partially correlated with long-term growth, while five are marginally related. The strongest evidence is for the initial level of real GDP per capita. The BACE method combines Bayesian model averaging with classical OLS estimation, using weights proportional to the likelihoods of each model. This approach allows for a more accurate estimation of variable importance in growth regressions by accounting for model uncertainty. The results show that variables with high inclusion probabilities are robustly related to growth, while others are only marginally related. The paper concludes that the data support the hypothesis that there is a set of variables robustly partially correlated with economic growth, contradicting the extreme bounds test which would reject the significance of every single variable. The BACE method provides a more nuanced understanding of variable importance in growth regressions compared to traditional methods.