A STOCHASTIC FRONTIER PRODUCTION FUNCTION
                                   INCORPORATING FLEXIBLE RISK PROPERTIES
                                     Guang H. Wan and George E. Battese
                                            No. 66 - June, 1992
                  ISSN     0 157-0188
                  ISBN     1 86389 018 1
                    A STOCKASTIC FRONTIER PRODUCTION FUNCTION
                                           +
                    INCORPORATING FLEXIBLE RISK PROPERTIES
                                          ~*
                     Guang H. Wan" and George E. Battese
                             ABSTRACT
           This paper considers a new stochastic frontier production function which
        permits the marginal production risks of inputs to be negative or positive
        and the technical efficiency of firms to be a function of the levels of the
        factor inputs.
           Previous frontier production function models, which have specified
        either zero or positive marginal risks, do not permit sufficient flexibility
        for many empirical applications. The proposed frontier model incorporates
        the production risk structure, suggested by Just and Pope (1978), and the
        stochastic frontier production function model, proposed by Aigner, Lovell and
        Schmidt (1977) and Meeusen and van den Broeck (1977).                          ~
           Maxlmum-llkellhood estimation of the parameters of the frontier
        production function and the prediction of technical efflciencies of firms are
        considered, given that cross-sectional data on sample firms are available.
           Paper presented at the Australasian Meeting of the Econometric Society,
           Monash University, Melbourne, 6-8 July 1992.
           Department of Agricultural Economics, University of Sydney (A04),
           NSW 2006, Phone: (02) 692 4814, Fax: (02) 692 2945.
           Department of Econometrics, University of New England, Armidale, NSW
           2351, Australia. Phone: (067) 73 2795, Fax: (067) 73 3205.