Statistical Methods in Finance 2018

Dec 17 - 20, 2018


A new class of asymmetric volatility models

by TV Ramanathan

In this talk, we consider a new class of asymmetric volatility models. The proposed class is formed by treating the parameters as a stationary and ergodic sequence of coefficients. This proposed family can nest several non-linear asymmetric generalized autoregressive conditional heteroskedastic (GARCH) models with stochastic parameters into its ambit. It also generalizes the Markov switching GARCH and Glosten, Jagannathan and Runkle (GJR) models. The geometric ergodicity of the proposed process is established. Sufficient conditions for stationarity and existence of moments have also been investigated. Geometric ergodicity of various volatility models with stochastic parameters has been discussed as special cases. An attempt has been made to address the related inference problems.