Semiparametric Efficient Estimation of AR(1) Panel Data Models

This study focuses on the semiparametric efficient estimation of random effect panel models containing AR(1) disturbances. We also consider such estimators when the effects and regressors are correlated (Hausman and Taylor, 1981). One motivation for such a model is the need to estimate a stochastic frontier distance function, isolate the fixed effects estimates, and interpret transformations of them as firm-specific relative efficiencies (Schmidt and Sickles, 1984). In markets in which regulatory constraints have been lessened or done away with, these market shocks may not be adjusted to immediately and may induce a serial correlation pattern in within firm variations. In the banking industry, whose productivity we analyze over the 1980's and 1990's, these aspects of semiparametric efficient estimation become important in order to resolve questions concerning the proper measurement of financial deregulation's impact on productivity. We introduce two semiparametric efficient estimators that make minimal assumptions on the distribution of the random errors, effects, and the regressors and that provide semiparametric efficient estimates of the slope parameters and of the effects. Our estimators extend the previous work of Park and Simar (1995), Park, Sickles, and Simar (1998), and Adams, Berger, and Sickles (1998).