Assessing the Value Risk (VAR) for BSE Index consisting of 30 stocks by using various parametric, nonparametric and semiparametric models for estimating Value-at-Risk (VAR)

Gupta, Ruchir (2008) Assessing the Value Risk (VAR) for BSE Index consisting of 30 stocks by using various parametric, nonparametric and semiparametric models for estimating Value-at-Risk (VAR). [Dissertation (University of Nottingham only)] (Unpublished)

[img] PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (945kB)

Abstract

The objective of this report is to estimate Value-at-Risk (VAR) for Bombay Stock Exchange (BSE) Index consisting of 30 stocks for a single day and 5-day period using various methods of assessment and comment on the best estimate for VAR.

In this report VAR theory and various models used to estimate VAR like Parametric models (GARCH, EWMA) and Semi-parametric model (Historical simulation methods and its variants) has been studied and explained. The report also explains the backtesting models to check the accuracy of results.

Finally, the models have been applied to BSE Sensitive Index (SENSEX) which consists of 30 stocks in different sectors of Indian economy. The key findings of this report is that Volatility Clustering is one of the most prominent stylized fact for the index due to which there is no single value for VaR which could explain the risk in the market for all times.

Rather, investors should base their decision on a range of VaR values based on the state of economy of the country (i.e. inflation, business cycle etc).

Item Type: Dissertation (University of Nottingham only)
Depositing User: EP, Services
Date Deposited: 12 Nov 2008
Last Modified: 30 Jan 2018 22:37
URI: https://eprints.nottingham.ac.uk/id/eprint/22164

Actions (Archive Staff Only)

Edit View Edit View