Monte Carlo study of growth regressions

Using Monte Carlo simulations, this paper evaluates the bias properties of estimators commonly used to estimate growth regressions derived from the Solow model. We explicitly allow for measurement error, country-specific fixed effects and regressor endogeneity. An OLS estimator applied to a single c...

Full description

Saved in:
Bibliographic Details
Published in:Journal of economic growth (Boston, Mass.) Mass.), 2009-06, Vol.14 (2), p.103-147
Main Authors: Hauk, William R. Jr, Wacziarg, Romain
Format: Article
Language:English
Subjects:
Correlations
Debates
Economic Growth
Economic growth models
Economic statistics
Economic theory
Economics
Economics and Finance
Error
Error rates
Estimates
Estimation bias
Estimators
Generalized method of moments
Growth models
Growth regressions
Human capital
Income estimates
Instrumental variables estimation
International Economics
Macroeconomics/Monetary Economics//Financial Economics
Measurement
Measurement error
Modeling
Monte Carlo simulation
Performance evaluation
Regression analysis
Sampling bias
Simulation
Statistical variance
Studies
System-GMM
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using Monte Carlo simulations, this paper evaluates the bias properties of estimators commonly used to estimate growth regressions derived from the Solow model. We explicitly allow for measurement error, country-specific fixed effects and regressor endogeneity. An OLS estimator applied to a single cross-section of variables averaged over time (the between estimator) performs best in terms of the extent of bias on each of the estimated coefficients. Fixed-effects and the Arellano–Bond GMM estimator overstate the speed of convergence under a wide variety of assumptions, while the between estimator understates it. Finally, fixed effects and Arellano–Bond bias towards zero the slope estimates on the human and physical capital accumulation variables, while the between estimator and the Blundell–Bond system GMM estimator bias these coefficients upwards.
ISSN:1381-4338
1573-7020
DOI:10.1007/s10887-009-9040-3