A0552
Title: The time-varying multivariate autoregressive index model
Authors: Barbara Guardabascio - University of Perugia (Italy) [presenting]
Gianluca Cubadda - University of Rome Tor Vergata (Italy)
Stefano Grassi - University of Rome 'Tor Vergata' (Italy)
Abstract: Many economic variables feature changes in their conditional mean and volatility, and time-varying vector autoregressive models are often used to handle such complexity in the data. Unfortunately, as the number of series grows, they present increasing estimation and interpretation problems. The attempt is to address this issue by proposing a new multivariate autoregressive index model that features time-varying mean and volatility. Technically, a new estimation methodology is developed that mixes switching algorithms with the forgetting factors strategy of a prior study. This substantially reduces the computational burden and allows one to select or weigh, in real-time, the number of common components and other features of the data without the further computational cost. Using US macroeconomic data, a forecasting exercise is provided that demonstrates the feasibility and usefulness of this new model.
