A0703
Title: Factor overnight GARCH-Ito models
Authors: Donggyu Kim - KAIST (Korea, South)
Minseog Oh - KAIST (Korea, South)
Xinyu Song - Shanghai University of Finance and Economics (China) [presenting]
Yazhen Wang - University of Wisconsin (United States)
Abstract: A unified factor overnight GARCH-Ito model is introduced for large volatility matrix estimation and prediction. To account for whole-day market dynamics, the proposed model has two different instantaneous factor volatility processes for the open-to-close and close-to-open periods. At the same time, each embeds the discrete-time multivariate GARCH model structure. To estimate latent factor volatility, the low rank plus sparse structure is assumed, and nonparametric estimation procedures are employed. Then, based on the connection between the discrete-time model structure and the continuous-time diffusion process, a weighted least squares estimation procedure is proposed with the nonparametric factor volatility estimator and its asymptotic theorems are established.
