- Advances in Chinese Economic Studies series
Shuji Yao, Zhongwei Han and Dan Luo
7. 7.1 SFA applications and robustness of DEA results MODEL SPECIFICATION The recent development of the efficiency literature is to use several frontier measures together to test the robustness of the results. As the most advanced parametric efficiency measure, the SFA approach offers the facility to examine the mathematical relationships assumed between input and output variables and the factors that may influence the efficiency of DMUs. In this chapter, an SFA model will be constructed for insurance companies in China, followed by the interpretation of the regression results and the correlation analysis of the efficiency results obtained by the SFA and DEA models. A flexible model has been developed (Aigner, Lovell and Schmidt, 1977) using a stochastic frontier that can move to compensate for errors. This frontier separates inefficiency from statistical noise. Coelli, Prasada Rao and Battese (1988) derived the following equation as a version of stochastic frontier approach: Y 5 f (b, x1, x2, x3 . . . xs) ? exp (v) ? exp (u) (E7.1) where xr, r = 1 . . . s, are the known input levels and b is a set of unknown parameters to be estimated. Y denotes the observed output level. f (b, xr) represents a deterministic kernel. The random error term v is normally distributed and the term u $ 0, assumed half-normal or exponentially distributed,1 reflects inefficiency. Thus, the estimated inefficiency of a unit is the difference between its observed output and the estimated maximum output feasible for its input level. The maximum likelihood method is used to estimate the...
You are not authenticated to view the full text of this chapter or article.
Elgaronline requires a subscription or purchase to access the full text of books or journals. Please login through your library system or with your personal username and password on the homepage.
Non-subscribers can freely search the site, view abstracts/ extracts and download selected front matter and introductory chapters for personal use.
Your library may not have purchased all subject areas. If you are authenticated and think you should have access to this title, please contact your librarian.