An Improved DCC Model Based on Large-Dimensional Covariance Matrices Estimation and Its Applications

The covariance matrix estimation plays an important role in portfolio optimization and risk management. It is well-known that essentially a convex quadratic programming problem, which also special case of symmetric cone optimization. Accurate will lead to more reasonable asset weight allocation. However, some existing methods do not consider the influence time-varying factor on estimations. To remedy this, this article, we propose improved dynamic conditional correlation model (DCC) by using nonconvex under smoothly clipped absolute deviation hard-threshold penalty functions. We first construct obtain optimal estimation, then use replace unconditional DCC model. result shows loss proposed estimator smaller than other variants numerical experiments. Finally, apply our classic Markowitz portfolio. results show performs better current models.