Partial least squares for dependent data

The partial least squares algorithm for dependent data realisations is considered. Consequences of ignoring the dependence for the algorithm performance are studied both theoretically and in simulations. It is shown that ignoring certain non-stationary dependence structures leads to inconsistent estimation. A simple modification of the partial least squares algorithm for dependent data is proposed and consistency of corresponding estimators is shown. A real-data example on protein dynamics llustrates a superior predictive power of the method and the practical relevance of the problem.