Affiliation:
1. Kalinga Institute of Industrial Technology , Deemed to be University , India
2. IGNOU , New Delhi , India
3. Independent Researcher
Abstract
Abstract
Research background
Many studies have been done in the field of predicting the Volatility of Commodities; however, very little or no analysis has been conducted on any sector, industry, or indices to identify which model is best to understand the asset’s characteristics, as there is a hypothesis that all financial time series can be interpreted by implementing the same model.
Purpose
The primary objective is to identify different tools developed by the researchers in estimating impulsive clustering and leverage effects. A comparison will be made among the available tools of the GARCH family models to suggest the best tool to forecast and calculate volatility with the least error.
Research methodology
The data used are historical time series data of Indian base metal indices, i.e., Aluminum (AL), Copper (CO), Lead (LE), Nickel (NI), and Zinc (ZI) from NSE for a period from 1st June 2012 to 31st August 2022 from the official website of NSE of India. The study compared and attempted to identify which GARCH family model is suitable to measure the volatility clustering and leverage effect in Indian base metal indices by reducing the chances of error.
Results
The study has revealed that the GRACH asymmetric models, while approximating and predicting the financial time series, can enhance the model’s output when it has a high frequency. Here, the asymmetric GARCH models (TARCH, CGARCH, EGARCH, and PARCH) better predict volatility than classic models.
Novelty
This study is original in its approach, as a previous study stated the presence of volatility or leverage effect by implementing any one tool. However, this study will compare available tools to suggest which is appropriate for which sector. This analysis will support future researchers and practitioners in evaluating volatility clustering and the effect of leverage by implementing the appropriate GARCH family model without believing in a hypothesis that a single model is good enough to predict volatility.
Reference48 articles.
1. AbdElaal, M.A. (2011). Modeling and forecasting time varying stock return volatility in the Egyptian stock market. International Research Journal of Finance and Economics, 78.
2. Aggarwal, R. (1988). Stock index futures and cash market volatility. Review of Futures Markets, 7(2), 290–299.
3. Akgül, I., Sayyan, H. (2005). İMKB-30 Hisse Senedi Getirilerinde Volatilitenin Asimetrik Koşullu Değişen Varyans Modelleri ile Öngörüsü. TC Marmara Üniversitesi Bankacılık ve Sigortacılık Yüksekokulu 2005 Geleneksel Finans Sempozyumu Tebliğleri.
4. Al Freedi, A., Shamiri, A., Isa, Z. (2012). A study on the behavior of volatility in Saudi Arabia stock market using symmetric and asymmetric GARCH models. Journal of Mathematics & Statistics, 8(1).
5. Ali, I. (2016). Stock Market Volatility and Returns: A Study of NSE & BSE in India. International Journal of Humanities & Social Science Studies, 202–211.