A Monte Carlo study of growth regressions

By William R. Hauk, Romain Wacziarg. 2009

380 citations recorded by the source corpus.

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.

Subfields: Economics and Econometrics

View Paper: https://www.semanticscholar.org/paper/478fc4471a87e7c470069018ace08175637bc5aa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Inequality and growth: the neglected time dimension (2013, positive): “17 More recently, relying on Monte Carlo simulations, Hauk and Wacziarg (2009) have demonstrated that these biases can be greatly exacerbated in presence of measurement error.”
The Political Economy of Linguistic Cleavages (2012, methodology): “16 Hauk and Wacziarg (2009), using simulations based on the Solow model, show”
On the Distribution of Education and Democracy (2008, methodology): “has also been proved to perform better than the firstdifference estimator in Monte Carlo simulations when variables are highly persistent (see Blundell and Bond, 1998) and measured with error (see Hauk and Wacziarg, 2006 ).Secondly,wecomplementthemeasureofaverage years of schooling, commonly used i”
The Price Elasticity of Electricity Demand in the United States: A Three-Dimensional Analysis (2017, methodology): “These methods are also sensitive to specification choices, measurement error, and weak instruments (Hauk and Wacziarg, 2009; Bun and Windmeijer, 2010; Bazzi and Clemens, 2013; Hauk, 2017).”
The size and composition of government expenditure (2007, background): “[20] Hauk, William and Romain Wacziarg (2003) “A Monte Carlo Study of Growth Regressions” unpublished draft, October.”
The Determinants of Economic Growth in European Regions (2014, background): “Combined with likely measurement errors of regional growth and its determinants, HAUK and WACZIARG (2009) warned against the naive use of lagged values of regressors as instrumental variables, since this could imply larger biases than the much simpler ordinary least squares (OLS) estimator…”
Democracy, Political Risks and Stock Market Performance (2015, positive): “Because neither of these assumptions can be tested, Hauk and Wacziarg (2009) have concluded in their Monte Carlo study that an even larger problem than the weak instruments of the system GMM, is the validity of its moment conditions, which leads to some bias in its results.”
System GMM estimation with a small sample (2009, methodology): “These values are the same as those selected by Blundell et al (2000) 4 Hauk and Wacziarg (2009) carry out Monte Carlo simulations for the convergence equation derived from the Solow model by directly introducing noise in the variables.”
The democratic transition (2013, positive): “For further details on the AB and BB estimators, and of their econometric properties in the context of crosscountry dynamic panel applications, see Hauk and Wacziarg (2009).”