Monte Carlo methods examine the accuracy of several production frontier approximating forms, estimators and methods to rank firms by level of predicted technical efficiency. Results show stochastic frontier methods superior to data envelopment analysis. The Cobb-Douglas approximating form is superior to the translog or generalized Leontief.
Details
Title
A COMPARISON OF VARIOUS FRONTIER ESTIMATION METHODS UNDER DIFFERING DATA GENERATION ASSUMPTIONS
Record Identifier
https://ageconsearch.umn.edu/record/15773
PURL Identifier
http://purl.umn.edu/15773
Language
English
Total Pages
21
Series Statement
Staff Paper 062000; Selected Paper from the Southern Agricultural Economics Association Annual Meetings, January 30-February 2, 2000, Lexington, Kentucky