Computing the Jacobian in spatial models : an applied survey

摘要

Despite attempts to get around the Jacobian in fitting spatial econometricmodels by using GMM and other approximations, it remains a central problemfor maximum likelihood estimation. In principle, and for smaller data sets,the use of the eigenvalues of the spatial weights matrix provides a very rapidand satisfactory resolution. For somewhat larger problems, including thoseinduced in spatial panel and dyadic (network) problems, solving the eigenproblemis not as attractive, and a number of alternatives have been proposed.This paper will survey chosen alternatives, and comment on their relative usefulness.