Mj. Delmoral et Mj. Valderrama, A PRINCIPAL COMPONENT APPROACH TO DYNAMIC REGRESSION-MODELS, International journal of forecasting, 13(2), 1997, pp. 237-244
In this paper we introduce a dynamic regression model that states how
an output is related to an input allowing future values forecasting. T
he basic tools to set up this model are the orthogonal decomposition o
f a discrete time stochastic process by means of its principal compone
nts analysis, and the linear regression performed on the principal com
ponents of input and output processes. The behaviour of this model is
empirically studied on real data, showing that low forecast errors are
obtained by using this model. A comparison between such a model and a
transfer function one, for a particular two time-series case, is disc
ussed. (C) 1997 Elsevier Science B.V.