CPR Working Paper Series No. 97
A Monte Carlo Study of Efficiency Estimates From Frontier Models
William C. Horrace and Seth O. Richards
August 2007
Abstract:
Parametric stochastic frontier models yield firm-level conditional distributions of inefficiency that are truncated normal. Given these distributions, how should one assess and rank firm-level efficiency? This study compares the techniques of estimating a) the conditional mean of inefficiency and b) probabilities that firms are most or least efficient. Monte Carlo experiments suggest that the efficiency probabilities are more reliable in terms of mean absolute percent error when inefficiency has large variation across firms. Along the way we tackle some interesting problems associated with simulating and assessing estimator performance in the stochastic frontier environment.
You can download a PDF version of the paper and view it and print it using a FREE copy of Adobe Acrobat Reader.
Click here for the Adobe Acrobat version of CPR Working Paper 97
Or
for more information on ordering a hard copy of this paper, please contact the Publications Officer, Center for Policy Research, 426 Eggers Hall, Syracuse University, Syracuse, New York 13244-1020 or e-mail our Publications Officer at puboff@maxwell.syr.edu. Each hard copy costs $5.00 (US) and payment should be included with mail order.