报告题目：A Combination of High and Low Frequencies Data in Portfolio Studies
报告人：刘成，武汉大学经济与管理学院
报告时间：2016年3月21日（周一）下午14:00-16:00
报告地点：数学楼二楼学术报告厅
报告摘要：The integrated covariance matrix (ICM) of financial assets and the inverse of it—integrated precision matrix(IPM), play crucial roles in many financial applications, such as the estimation of the IPM is the foundation of portfolio choice problems.In this paper, we propose new estimators of a vast dimensional ICM and IPM by combining two different frequencies data and apply our estimator of the IPM in portfolio choice problems. We show that (1) our estimators are positive definite for any dimensional ICM and IPM whose dimensions p can go to infinity and can even than the number of observations; (2) the estimators are asymptotic optimal in the class of estimators which shrinkage the eigenvalues of a per-designed covariance matrix; (3) the computational speeds of our estimators are quite fast even when p is very large as we translate the estimation of a large p dimensional matrix to p one-dimensional estimation problems. Advantages of our estimators are demonstrated by real data analysis.