Formes et méthodes d’estimation des systèmes récursifs dynamiques à double indice

The purpose of this paper is to study the model belongs to the family of structural equation models with data varying both across individuals (sectors) and in time. A complete theoretical analysis is developed in this work for the case of a dynamic recursive structure. Maximum likelihood estimation and SUR-GLS “Seemingly Unrelated Regressions-Generalized Least Square” estimators (iterated or not, with proper instruments and with Taylor’s transformation) are carefully used. These last convergent estimators are most efficient. The application of these methods to panel sector of morocco’s economy is treated in another paper.