GMMCOVEARN: A Stata Module for GMM Estimation of the Covariance Structure of Earnings

This note describes and illustrates a new Stata program, gmmcovearn, that estimates the covariance structure of earnings for a variety of models using the GMM estimator. The program estimates models that incorporate time factor loadings and cohort factor loadings on both the transitory and permanent component, allows the transitory component to follow either an AR(1) or an ARMA(1,1) process and allows for a random growth and/or random walk process on the permanent component. The program has been used in recent papers by Doris et al (2010a, 2010b).