Journal of Econometrics 3 (1975) 35-50.

SEEMINGLY UNRELATED NONLINEAR REGRESSIONS

A. Ronald GALLANT^*

North Carolina State University, Raleigh, NC 27607, U.S.A.

Received January 1974, revised version received June 1974

Abstract: The article considers the estimation of the parameters of a set of nonlinear regression equations when the responses are contemporaneously but not serially correlated. Conditions are set forth such that the estimators obtained is strongly consistent, asymptotically normally distributed, and asymptotically more efficient than the single-equation least squares estimator. The methods presented allow estimation of the parameters subject to nonlinear restrictions across equations. The article includes a discussion of methods to perform the computations and a Monte Carlo simulation.