A STUDY ON ESTIMATING ACCURACY OF VALUE AT RISK MODELS IN EVALUATING RISK IN EQUITY INVESTMENTS

Abstract

The dissertation aims to investigate the efficiency and accuracy of various methods available for computation of Value at Risk (VaR) for equity investments in India. The quoting of Value-at-Risk (VaR) has become a standard practice of measure of market risk adopted by banks, trading firms, mutual funds and others, including even the non-financial firms. But any risk measure is useful and reliable only insofar as it can be verified for its accuracy. Value at Risk (VaR) is defined as the maximum potential change in value of a portfolio of financial instruments with the given probability over a certain time horizon. VaR measures can have various applications, such as in risk management, to evaluate the performance of risk takers and for regulatory requirements. Hence it is very important to develop methodologies that provide accurate estimates. The main objective of this study is to evaluate the performance of the most popular VaR methodologies such as Historical Simulation, Exponentially Weighted Moving Average (EWMA) model and the Monte Carlo simulation using Geometric Brownian Motion (GBM) model, paying particular attention to their underlying assumptions and to their logical flaws. For this purpose, the historical data on 25 stocks listed on National Stock Exchange (NSE) and other popular Equity Indexes have been considered. The evaluated VaR value has been then back-tested with the actual returns and the hypothesis been tested using Chi-Square Test to evaluate the accuracy of VaR model. Also limitations of the VaR models have been examined.