Cluster-based regularized sliced inverse regression for forecasting macroeconomic variables

This article concerns the dimension reduction in regression for large dataset. We introduce a new method based on the sliced inverse regression approach, called cluster-based regularized sliced inverse regression. Our method not only keeps the merit of considering both response and predictors information, but also enhances the capability of handling highly correlated variables. It is justified under certain linearity conditions. An empirical application on Stock and Watson (2011) macroeconomic dataset shows that our method outperformed the dynamic factor model and other shrinkage methods. ∗Zhihong Chen acknowledges financial support from the NSF of China (Grant 71101030)