Assessing the Performance of Value-at-Risk Models in London Stock Market

In this paper, parametric, nonparametric, and semi parametric models are applied to a hypothetical portfolio consisting a single asset - FTSE 100 Index, to assess their performance in the London stock market. In order to assess the performance of different approaches, the statistic features such as...

Full description

Bibliographic Details
Main Author: PHAN, Ha
Format: Dissertation (University of Nottingham only)
Language:English
Published: 2009
Online Access:https://eprints.nottingham.ac.uk/23213/
Description
Summary:In this paper, parametric, nonparametric, and semi parametric models are applied to a hypothetical portfolio consisting a single asset - FTSE 100 Index, to assess their performance in the London stock market. In order to assess the performance of different approaches, the statistic features such as kurtosis, skewness and autocorrelation of daily return have been studied. In addition, this article analyzes the advantages and disadvantages of each model and implements back-tests to check the validation of them. The main finding of this article is that NGARCH and GARCH(1,1)-t(d) model are the most accurate and reliable models to estimate Value at Risk in London Stock market.