EFFICIENT INFERENCE ON COINTEGRATION PARAMETERS IN STRUCTURAL ERROR-CORRECTION MODELS

This paper proposes inferential procedures for error correction models in structural form. Particular attention is paid to the issues of exogeneity of conditioning variables and identification of cointegration parameters as well as short-run parameters. The model leads to two classes of estimators and associated test statistics, depending on the exogeneity status of the conditioning variables. A Monte Carlo experiment shows how their asymptotic properties are reflected in finite sample behaviour.