Identification of the Covariance Structure of Earnings Using the GMM Estimator

In this paper we study the performance of the GMM estimator in the context of the covariance structure of earnings. Using analytical and Monte Carlo techniques we examine the sensitivity of parameter identification to key features such as panel length, sample size, the degree of persistence of earnings shocks and the evolution of inequality over time. We show that the interaction of transitory persistence with the time pattern of inequality determines identification in these models and offer some practical recommendations that follow from our findings.