Publication Type : Conference Proceedings
Publisher : Advances in Intelligent Systems and Computing
Source : Advances in Intelligent Systems and Computing, 2019, 898, pp. 609–618.
ISBN : 9789811333927
Keywords : Box Cox transformation, Error variance, Heteroskedasticity, Modelling and analysis, Signal processing, Soft computing, Stock exchange, Time series, Time series analysis, Time series models, Time-series data, Volatility
Campus : Bengaluru
School : School of Engineering
Department : Electronics and Communication
Year : 2018
Abstract : The comprehension of volatility is a crucial concept in analysing data. It is of greater importance for financial data since it furnishes key aspects such as return on investments and helps with effective hedging. The unpredictable nature of volatility causes heteroskedasticity which leads to difficulty in modelling. Consequently, time series models are desirable to predict volatility. An illustration of the same has been shown through an example of fitting time series models on the volatility of a listing from the National Stock Exchange (NSE). This paper also attempts to treat heteroskedasticity using Box-Cox transformations to achieve equal error variances prior to the modelling. © Springer Nature Singapore Pte Ltd. 2019.
Cite this Research Publication : Somarajan, S., Shankar, M., Sharma, T., Jeyanthi, R., “Modelling and analysis of volatility in time series data”, Advances in Intelligent Systems and Computing, 2019, 898, pp. 609–618.