This paper proposes a model suitable for exploiting fully the information contained in mixed frequency and mixed sample data in the estimation of cointegrating vectors. The asymptotic properties of easy-to-compute spectral regression estimators of the cointegrating vectors are derived and these estimators are shown to belong to the class of optimal cointegration estimators. Furthermore, Wald statistics based on these estimators have asymptotic chi-square distributions which enable inferences to be made straightforwardly. Simulation experiments suggest that the finite sample performance of a spectral regression estimator in an augmented mixed frequency model is particularly encouraging as it is capable of dramatically reducing the root mean squared error obtained in an entirely low frequency model to the levels comparable to an infeasible high frequency model. The finite sample size and power properties of the Wald statistic are also found to be good. An empirical example, to stock price and dividend data, is provided to demonstrate the methods in practice.
展开▼
