A cross-country comparison of Expected Shortfall estimation models

Du, Cong (2017) A cross-country comparison of Expected Shortfall estimation models. [Dissertation (University of Nottingham only)]

[img] PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB)

Abstract

This dissertation aims to find a better-performed model in estimating risk measures for certain countries. The risk measures are estimated under five distributional assumptions (normal, Student-t, skewed Student-t, historical distribution, and generalized pareto) for five financial markets (Nasdaq, FTSE100, SSEC, BVSP, and Nifty50), three estimation windows (250, 500, 1000), and two significance levels (0.05 and 0.01). A two-stage ES backtest and a direct ES test are conducted. The violation ratio comparisons and the backtesting results indicate that student’s t distribution and normal distribution have overall the best and the worst performance. Unconditional models also have its deficiencies in modeling financial markets.

Item Type: Dissertation (University of Nottingham only)
Depositing User: Du, Cong
Date Deposited: 12 Apr 2018 09:19
Last Modified: 17 Apr 2018 15:07
URI: http://eprints.nottingham.ac.uk/id/eprint/46082

Actions (Archive Staff Only)

Edit View Edit View