Doubly Heteroscedastic stochastic production frontiers with an application to English cereal farms
Paper number: 99/08
Paper date: February 1999
Paper Category: Discussion Paper
K. Hadri*, City University, London
C Guermat and J Whittaker, University of Exeter
In previous studies, measures of technical inefficiency derived from stochastic production frontiers have been estimated from residuals which are sensitive to specification errors. This study corrects for this inaccuracy by extending the doubly heteroscedastic stochastic cost frontier suggested by Hadri (1999) to stochastic production frontier and to panel data. The extended correction for heteroscedasticity is supported by the data. The study uses data on 102 mainly cereal farms in England, and not only estimates technical efficiency but also examines the links between the efficiency of cereal production, cereal area, chemical usage and labour usage. These links are explored because European Union agricultural policy is no longer narrowly concerned solely with farm income levels and productivity, but also embraces environmental quality and rural development concerns. Whenever there are multiple policy goals it is important to gain an understanding of whether there is conflict or complementarity between them.
JEL Classification Nos: C23, C24, D24, Q12
Keywords: Stochastic frontier production, heteroscedasticity, technical efficiency, farm size, panel data, environment.
* We would like to thank Gordon Harris, Bernard Pearson, and Liz Webber for their help with computing problems and Sue Milward for the IT services for her help with the data. The first author gratefully acknowledges the hospitality of the School of Business and Economics at the University of Exeter and thanks the Head of School, Mr Martin Timbrell.
Corresponding Author: Dr Kaddour Hadri, City University, Northampton Square, London, EC1 0HB, UK