Kansas State University

Estimation of Multiproduct Cost Function for Multiple Technology Industry Using Gibbs Sampling

Email address: leilannie508@yahoo.com

Keywords: multiproduct cost function, economies of scale and scope, agricultural bank industry, Gibbs sampling

JEL Classifications: C, D, E, G, H, M

Abstract:
In this study the assumption of simultaneous existence of multiple technologies of production is incorporated in modeling multiproduct cost function. This particular assumption is essential especially for an industry undergoing a transition period of adopting a new technology or regulatory changes. A Bayesian method using Gibbs sampling is developed to estimate the multiproduct cost function as a stochastic switching regression model. The estimated multiproduct cost function is utilized to evaluate the degree and direction of overall and product-specific economies of scale and scope of banks in Kansas offering agricultural loans. The standard regression model and the stochastic switching regression model provide coefficients differing in magnitude and sign which are also reflected in varying magnitude and direction of the overall and product-specific economies of scale and scope. These results imply that the traditional regression model may provide misleading estimates of the cost function coefficients under multiple technologies of production. Another interesting result is that the stochastic switching regression model provides coefficients with smaller standard errors.

PDF file of paper: odejar.pdf

Session: Production, Consumption and Productivity

Time: Friday, 6 July, 3:30pm - 5pm

Room: F