Reduced Rank Regression Models in Economics and Finance

This chapter surveys the importance of reduced rank regression techniques (RRR) for modelling economic and ?nancial time series. We mainly focus on models that are capable to reproduce presence common dynamics among variables such as serial correlation feature multivariate autoregressive index models. Cointegration analysis, which RRR plays a central role, is not discussed in this it deserves speci?c treatment its own. Instead, we show how detect model comovements series stationary or have been stationarized after proper transformations. The motivations use econometrics include dimension reductions simplify complex thus making interpretations easier, well pursuing e¢ ciency gains both estimation prediction. Via ?nal equation representation, also makes nexus between parsimonious marginal ARIMA drawback RRR, all reduction techniques, underlying restrictions may be present data. provide couple empirical applications illustrate concepts methods.