Estimation of Conditional Covariance Matrices for a Class of High-Dimensional Varying Coefficient Factor-Generalized Autoregressive Conditional Heteroscedasticity Model

This paper explores a class of High-Dimensional Varying Coefficient Factor-GARCH (Generalized Autoregressive Conditional Heteroscedasticity) model, designed to capture dynamic relationships between variables and account for the heterogeneity of time series data. By exploiting the structure of the model, a mixed approach is proposed to estimate conditional covariance matrices. Furthermore, asymptotic properties for the estimators are established, providing a theoretical foundation for their consistency and efficiency. A simulation study is conducted to demonstrate the performance of estimators, and a real data example of portfolio allocation is presented to illustrate the practical application of the approach.