Multilinear models with time-varying parameters

Abstract

A class of multilinear models for nonlinear time series is introduced. It extends the bilinear ARMA representation of Granger-Andersen by including general monomials of lagged input and output. For this class, algorithms of structure identification and parameter estimation are provided, suitable for dealing with subset models and time-varying coefficients. An extended application on real economic data illustrates the framework and makes comparisons with other nonlinear models.