Title: High-dimensional predictive quantile regression with mixed roots
Authors: Rui Fan - Rensselaer Polytechnic Institute (United States) [presenting]
Ji Hyung Lee - University of Illinois at Urbana-Champaign (United States)
Abstract: The benefit of using adaptive LASSO for predictive quantile regression is studied. The commonly used predictors in predictive quantile regression typically have various degrees of persistence, and exhibit different signal strength in explaining the conditional quantiles of dependent variable. We show that the adaptive LASSO methods have the consistent variable selection and the oracle properties under the simultaneous presence of stationary, unit root and cointegrated predictors. Some encouraging simulation results are reported.