Asymptotic Properties of the Estimator of the Long-run Coefficient in a Dynamic Model with Integrated Regressors and Serially Correlated Errors

In this paper we examine the asymptotic properties of the estimator of the long-run coefficient (LRC) in a dynamic regression model with integrated regressors and serially correlated errors. We show that the OLS estimators of the regression coefficients are inconsistent but the OLS-based estimator of the LRC is superconsistent. Furthermore, we propose an alternative consistent estimator of the LRC, compare the two estimators through a Monte Carlo experiment, and Þnd that the proposed estimator is MSE-superior to the OLS-based estimator. JEL ClassiÞcation numbers: C13, C15, C22 ∗The authors are grateful to Kimio Morimune, Adrian Pagan, Katsuto Tanaka, Taku Yamamoto, seminar participants at Hitotsubashi University and University of Western Australia for helpful comments on an earlier version of this paper. The Þrst author wishes to thank the Department of Economics at the University of Western Australia for its hospitality during a visit in 1997, and the second author wishes to acknowledge the Þnancial support of the Australian Research Council abd the Institute of Social and Economic Research at Osaka University. This paper was revised while the second author was a Visiting Scholar from Abroad at the Institute.