Modeling Symmetric and Asymmetric Volatility in Nifty 50 Index Futures Market

Abstract

Volatility in stock markets is a matter of concern for investors and policymakers across the world. Derivatives enable traders to manage risk arising out of volatility through hedging and arbitrage (Singh & Kansal, 2010). During times of high volatility, regulatory authorities step in to curb the frenzied activity in the stock market. Time series data of financial nature shows non-normality traits. Thus, it is essential to check whether distributions other than normal distribution can perfectly analyze the time series data. Therefore, it becomes important to use the appropriate methods to model volatility. This study aims to analyse both symmetric and asymmetric volatility in Nifty 50 futures markets. Different variants of GARCH models were used in the study under three probability distributions such as normal, Student’s-t, and generalized error distribution (GED). EGARCH (1,1) model with Student’s- t distribution proved to be the best model for capturing volatility as it had the lowest AIC value. The results detected the presence of a leverage effect and thereby confirmed that negative news created more volatility than positive news.