Estimation of a Dynamic Multilevel Factor Model with possible long-range dependence

Abstract

A dynamic multilevel factor model with possible stochastic time trends is proposed. In the model, long-range dependence and short memory dynamics are allowed in global and regional common factors as well as model innovations. Estimation of global and regional common factors is performed on the prewhitened series, for which the prewhitening parameter is estimated semiparametrically from the cross-sectional and regional average of the observable series. Employing canonical correlation analysis and a sequential least-squares algorithm on the prewhitened series, the resulting multilevel factor estimates have a centered asymptotic normal distribution. Selection of the number of global and regional factors is also discussed. Estimates are found to have good small-sample performance via Monte Carlo simulations. The method is then applied to the Nord Pool electricity market for the analysis of price comovements among different regions within the power grid. The global factor is identified to be the system price, and fractional cointegration relationships are found between regional prices and the system price.