Estimation and Inference in Parametric Stochastic Frontier Models: A SAS/IML Procedure for a Bootstrap Method

Parametric Stochastic Frontier Models are widely used in productivity analysis and are commonly estimated using FRONTIER, STATA or LIMDEP packages, which only provide point estimates for firm-specific technical efficiency. Confidence intervals for technical efficiencies with superior coverage properties than those offered by the Horrace and Schmidt (1996) method may be computed using the Bootstrap method introduced by Simar and Wilson (2005). To facilitate these calculations, we propose a SAS/IML procedure, which computes these confidence intervals for stochastic frontier models with or without inefficiency effects. We apply the program to estimating supermarket-specific technical efficiency in the U.S. Results indicates that the program works very well and produce narrower confidence intervals than those obtain using Horrace and Schmidt (1996) method.


Issue Date:
2006-08
Publication Type:
Report
PURL Identifier:
http://purl.umn.edu/149177
Total Pages:
27
Series Statement:
Research Report
095




 Record created 2017-04-01, last modified 2017-08-27

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)