A0781
Title: The vector error correction index model: Representation and statistical inference
Authors: Marco Mazzali - University of Rome Tor Vergata (Italy)
Gianluca Cubadda - University of Rome TV (Italy) [presenting]
Abstract: The multivariate index autoregressive model is extended to the case of cointegrated time series of order (1,1). In this new modelling, which we call the Vector Error-Correction Index Model (VECIM), the first differences of cointegrated time series are driven by some linear combinations of the variables that are labelled as the indexes. When the number of indexes is small compared to the sample size, the VECIM achieves a significant dimension reduction w.r.t. the classical Vector Error Correction Model (VECM), thus allowing to analyze cointegration even in medium vector autoregressive models, a setting where maximum likelihood inference for the VECM does not work well. We show that the indexes follow a VECM of smaller dimension than the number of series, that the VECIM allows decomposing the reduced form shocks into sets of common and uncommon shocks, and that the former can be further decomposed into permanent and transitory shocks. Moreover, we offer a switching algorithm to estimate the parameters of the VECIM optimally. Finally, we document the practical value of the proposed approach through both simulations and an empirical application. In particular, we search for the shocks that drive the aggregate fluctuations at different frequency bands in the US. We find that a common transitory shock generates most of the variability at the business cycle frequencies, whereas a common permanent shock drives the long run.
