A fully nonparametric stochastic frontier model for panel data

In this paper we estimate the frontier and time variant technical efficiency fully nonparametrically by exploiting recent advances in kernel regression estimation of categorical data. Specifically, we model firm (unordered) and time (ordered) categorical variables directly into the conditional mean. This approach allows us to smooth the firm and time specific effects, which formally entered the model linearly. Our setup allows for more flexible and accurate estimates of the frontier and time variant technical efficiency. Further, the estimators are consistent and achieve the standard nonparametric rate of convergence. We apply these techniques to a data set examining labor efficiencies of 17 railway companies over a period of 14 years. Not only are our results for the elasticites more economically intuitive than theparametric and semiparametric procedures, we obtain different rankings in terms of labor efficiencies.

[1]  Q. Lib,et al.  Nonparametric estimation of regression functions with both categorical and continuous data , 2004 .

[2]  A. Ullah,et al.  Nonparametric Econometrics , 1999 .

[3]  Léopold Simar,et al.  Semiparametric efficient estimation of AR(1) panel data models. , 2003 .

[4]  Robin C. Sickles,et al.  Semiparametric Approaches to Stochastic Panel Frontiers With Applications in the Banking Industry , 1999 .

[5]  Byeong-Ho Gong,et al.  Finite sample evidence on the performance of stochastic frontiers and data envelopment analysis using panel data , 1992 .

[6]  J. V. Ryzin,et al.  A class of smooth estimators for discrete distributions , 1981 .

[7]  Qi Li,et al.  Nonparametric Econometrics: Theory and Practice , 2006 .

[8]  Léopold Simar,et al.  A general framework for frontier estimation with panel data , 1996 .

[9]  Robin C. Sickles,et al.  Panel estimators and the identification of firm-specific efficiency levels in parametric, semiparametric and nonparametric settings , 2005 .

[10]  Léopold Simar,et al.  Efficient Semiparametric Estimation in a Stochastic Frontier Model , 1994 .

[11]  Jeffrey S. Racine,et al.  CROSS-VALIDATED LOCAL LINEAR NONPARAMETRIC REGRESSION , 2004 .

[12]  J. Aitchison,et al.  Multivariate binary discrimination by the kernel method , 1976 .

[13]  Léopold Simar,et al.  Iterated bootstrap with applications to frontier models , 1995 .

[14]  Léopold Simar,et al.  Stochastic Frontiers: A Semiparametric Approach , 1993 .

[15]  P. Schmidt,et al.  Production Frontiers and Panel Data , 1984 .

[16]  Yanqin Fan,et al.  Semiparametric Estimation of Stochastic Production Frontier Models , 1996 .

[17]  Cheng Hsiao,et al.  Panel Data Models , 2007 .