Subgeometrically ergodic autoregressions

In this paper we discuss how the notion of subgeometric ergodicity in Markov chain theory can be exploited to study the stability of nonlinear time series models. Subgeometric ergodicity means that the transition probability measures converge to the stationary measure at a rate slower than geometric. Specifically, we consider higher-order nonlinear autoregressions that may exhibit rather arbitrary behavior for moderate values of the observed series and that behave in a near unit root manner for large values of the observed series. Generalizing existing first-order results, we show that these autoregressions are, under appropriate conditions, subgeometrically ergodic. As useful implications we also obtain stationarity and β-mixing with subgeometrically decaying mixing coefficients.