ROBUSTIFYING AND SIMPLIFYING HIGH-DIMENSIONAL REGRESSION WITH APPLICATIONS TO YEARLY STOCK RETURN AND TELEMATICS DATA

Abstract The availability of many variables with predictive power 53-264817 makes their selection in a regression context difficult.This study considers robust and understandable low-dimensional estimators as building blocks to improve overall predictive power by optimally combining these building blocks.Our new algorithm is based on generalized cr

This work describes the preparation and the characterization of various samples of metallic Sn electroplated on a cupper foil under different current and time regimes.These samples wd ultrastar dc hc530 have been characterized by XRD and SEM and tested as negative electrodes in a cell using lithium foil as the counter electrode.The best electrode h