Advances and Applications in Statistics
Volume 64, Issue 2, Pages 165 - 180
(October 2020) http://dx.doi.org/10.17654/AS064020165 |
|
GMM ESTIMATION OF A COPULA-BASED STOCHASTIC FRONTIER MODEL
Arabinda Das
|
Abstract: This paper relaxes one of the distributional assumptions of independence of the error components that characterize most composed error formulations of the stochastic frontier models appearing in the literature by copula approach of modeling. Generalized method of moment (GMM) estimation procedures are presented that enable various degrees of distributional flexibility that are typically difficult to attain in likelihood-based approaches to estimation of frontier models. The popularly used FGM copula is used to capture the correlation between the error components-random noise and technical inefficiency. Moment-based specification tests for independence are also described. Some properties of the estimations are illustrated via the Monte Carlo simulation. An empirical example is provided by estimating a cost function using the cross-section data of electric utility behavior. |
Keywords and phrases: stochastic frontier model, Copula function, Ginni’s mean differences, generalized method of moments estimation.
|
|
Number of Downloads: 210 | Number of Views: 584 |
|