Modelling transmission of potato price volatility in West Bengal markets : MGARCH approach

Abstract

Volatility is a common phenomenon which can be observed in the financial market. Volatility is often considered to be same as risk, but the truth is, risk deals with only negative shocks whereas volatility takes care of both negative and positive shocks. It is important to model and forecast volatility efficiently as it involves a large domain of stakeholders. In present global scenario where markets are no more operating in isolation and trade taking place across markets at domestic and international levels, there exist an influence of one market upon the other. Under these circumstances the very popular GARCH model [1] which is univariate in nature seems restrictive in modelling and forecasting volatility. Hence, the multivariate GARCH (MGARCH) models were introduced to capture the movement of volatility among different markets. Various MGARCH models have been proposed in the literature. The most commonly used ones are BEKK (Baba, Engle, Kraft and Kroner), CCC (Constant Conditional Correlation) and DCC (Dynamic Conditional Correlation) modifications. In this paper, various MGARCH models have been explained in details highlighting their usefulness in capturing different volatility transmission process. Further, real data sets have been analysed using these models and the volatility transmission processes explained as a part of an illustration.