Consistent Estimation of Linear Panel Data Models with Measurement Error

Measurement error causes a downward bias when estimating a panel data linear regression model. The panel data context offers various opportunities to derive moment conditions that result in consistent GMM estimators. We consider three sources of moment conditions: (i) restrictions on the intertemporal covariance matrix of the errors in the equations, (ii) heteroskedasticity and nonlinearity in the relation between the error-ridden covariate and another, error-free, covariate in the equation, and (iii) nonzero third moments of the covariates. In a simulation study we show that these approaches work well.

Keywords: measurement error, panel data, third moments, heteroskedasticity, GMM

JEL Classification: C230, C260

Suggested Citation: Suggested Citation

Meijer, Erik and Spierdijk, Laura and Wansbeek, Tom, Consistent Estimation of Linear Panel Data Models with Measurement Error (January 26, 2015). CESifo Working Paper Series No. 5164, Available at SSRN: https://ssrn.com/abstract=2555580 or http://dx.doi.org/10.2139/ssrn.2555580