Hierarchical Bayesian Model for Technical Efficiency Using Stochastic Frontier Production Function

• Activity Number: 21
• Type: Topic Contributed
• Date/Time: Sunday, August 4, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Seongho Song*+ and Chansoo Kim and Younshik Chung and Myoungjin Jung
• Companies: University of Cincinnati and Kongju National University and Pusan National University and Pusan National University
• Keywords: Hierarchical Model ; Stochastic Frontier Production Function ; Technical Efficiency ; Markov Chain Monte CArlo

Abstract

A stochastic frontier production function has been considered in the case that there is the effect of non-negative technical inefficiency in the data. In the past decades, many studies have been discussed to determine the explanatory variables which affect the technical inefficiency effects in the stochastic frontier production function. We consider a hierarchical model of the stochastic frontier production function to investigate the data which has multiple hierarchical structures. It turns out that the proposed model naturally gives us the dependent covariance structure within a sub-group and the independence between sub-groups. We consider Bayesian analysis to estimate the model parameters in the model as well as the inefficiency model using Markov Chain Monte Carlo (MCMC).