Stochastic Nonparametric Envelopment of Data: Cross-Sectional Frontier Estimation Subject to Shape Constraints

30 Pages Posted: 2 May 2007

See all articles by Timo Kuosmanen

Timo Kuosmanen

Turku School of Economics

Mika Kortelainen

University of Joensuu

Date Written: May 1, 2007

Abstract

The field of production frontier estimation is divided between the parametric Stochastic Frontier Analysis (SFA) and the deterministic, nonparametric Data Envelopment Analysis (DEA). This paper explores an amalgam of DEA and SFA that melds a nonparametric frontier with a stochastic composite error. Our model imposes the standard SFA assumptions for the inefficiency and noise terms. The frontier is estimated nonparametrically, imposing monotonicity and convexity as in DEA. For estimation, we propose two alternative methods based on shape constrained nonparametric least squares. The performance of the proposed estimation techniques is examined using Monte Carlo simulations and an illustrative application.

Keywords: nonparametric least squares, method of moments, productive efficiency, pseudolikelihood, stochastic frontier analysis (SFA), data envelopment analysis (DEA)

JEL Classification: C14, C51, D24

Suggested Citation

Kuosmanen, Timo and Kortelainen, Mika, Stochastic Nonparametric Envelopment of Data: Cross-Sectional Frontier Estimation Subject to Shape Constraints (May 1, 2007). Available at SSRN: https://ssrn.com/abstract=983882 or http://dx.doi.org/10.2139/ssrn.983882

Timo Kuosmanen (Contact Author)

Turku School of Economics ( email )

FIN-20500 Turku
Finland

HOME PAGE: http://https://www.utu.fi/en/people/timo-kuosmanen

Mika Kortelainen

University of Joensuu ( email )

Finland