Estimation of a Panel Data Model with Parametric Temporal Variation in Individual Effects

This paper considers models with time-varying individual effects (also known as factor models). The paper extends Ahn, Lee and Schmidt, Journal of Econometrics, 2001 and Bai, Econometrica, 2003 to allow a parametric function of time for the time factor. It provides a fixed-effects treatment of random effects models suggested by Kumbhakar and by Battese and Coelli for the frontier production function problem. The paper presents a number of GMM estimators based on assumptions of different strengths. Least squares has unusual properties: consistency depends on white noise errors, and given white noise errors it is less efficient than a GMM estimator. The model is applied to the measurement of the cost efficiency of Spanish banks