Estimation of persistence in log-volatility using panel data

Abstract

This study proposes a stochastic volatility model for panel data, and estimation methods of its persistence parameter, in the case of large number of individuals and small number of time periods. In this study, two types of estimators for this model are presented, in accordance with the framework of the dynamic panel data model and the generalized method of moments. To examine and compare the two types of the estimators, Monte Carlo experiments are carried out. Furthermore, an empirical application to data of stock returns is implemented using these estimators.