Department of Economics
University of Arizona
Institutional Affiliation: University of Wisconsin
NBER Working Papers and Publications
|April 2010||Measurement Errors in Investment Equations|
with , : w15951
We use Monte Carlo simulations and real data to assess the performance of alternative methods that deal with measurement error in investment equations. Our experiments show that individual-fixed effects, error heteroscedasticity, and data skewness severely affect the performance and reliability of methods found in the literature. In particular, estimators that use higher-order moments are shown to return biased coefficients for (both) mismeasured and perfectly-measured regressors. These estimators are also very inefficient. Instrumental variables-type estimators are more robust and efficient, although they require fairly restrictive assumptions. We estimate empirical investment models using alternative methods. Real-world investment data contain firm-fixed effects and heteroscedasticity, c...
Published: Measurement Errors in Investment Equations (with H. Almeida and A. Galvao), Review of Financial Studies, 2010 (23), 3279-3328. [Lead article.]