Determinants of Long-Term Growth: A Bayesian Averaging of Classical Estimates (BACE) Approach

This paper examines the robustness of explanatory variables in cross-country economic growth regressions. It introduces and employs a novel approach, Bayesian Averaging of Classical Estimates (BACE), which constructs estimates by averaging OLS coefficients across models. The weights given to individ...

Full description

Saved in:
Bibliographic Details
Published inThe American economic review Vol. 94; no. 4; pp. 813 - 835
Main Authors Xavier Sala-i-Martin, Doppelhofer, Gernot, Miller, Ronald I.
Format Journal Article
LanguageEnglish
Published Nashville American Economic Association 01.09.2004
Subjects
Bayesian analysis
Bayesian method
Censuses
Economic growth
Economic growth models
Economic growth rate
Economic models
Economists
Enrollments
Estimates
Estimating techniques
Estimation
Ethnolinguistics
Gross domestic product
Manycountries
Population density
Population education
Population growth rate
Regression analysis
Socioeconomics
Studies
Variables
Online AccessGet full text

Cover

More Information
Summary:This paper examines the robustness of explanatory variables in cross-country economic growth regressions. It introduces and employs a novel approach, Bayesian Averaging of Classical Estimates (BACE), which constructs estimates by averaging OLS coefficients across models. The weights given to individual regressions have a Bayesian justification similar to the Schwarz model selection criterion. Of 67 explanatory variables we find 18 to be significantly and robustly partially correlated with long-term growth and another three variables to be marginally related. The strongest evidence is for the relative price of investment, primary school enrollment, and the initial level of real GDP per capita.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0002-8282
1944-7981
DOI:10.1257/0002828042002570