The Role of "Leads" in the Dynamic OLS Estimation of Cointegrating Regression Models

In this paper, we consider the role of "leads" of the first difference of integrated variables in the dynamic OLS estimation of cointegrating regression models. We demonstrate that the role of leads is related to the concept of Granger causality and that in some cases leads are unnecessary in the dynamic OLS estimation of cointegrating regression models. Based on a Monte Carlo simulation, we find that the dynamic OLS estimator without leads substantially outperforms that with leads and lags; we therefore recommend testing for Granger noncausality before estimating models.