Authors

Xiao Zhang

Type

Text

Type

Dissertation

Advisor

Rachev, Svetlozar | Chen, Xinyun | Kim, Aaron | Xiao, Keli | Djuric, Petar.

Date

2015-12-01

Keywords

Applied mathematics | Back testing, Dynamic volatility process, Regime Switching model

Department

Department of Applied Mathematics and Statistics.

Language

en_US

Source

This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree.

Identifier

http://hdl.handle.net/11401/76549

Publisher

The Graduate School, Stony Brook University: Stony Brook, NY.

Format

application/pdf

Abstract

This thesis is to incorporate Markov Regime Switching model with Fractionally Integrated process in order to capture abrupt change and regime persistence simultaneously in long memory dynamic volatility process. We adapt truncated ARCH\(\infty\) to estimation scheme of our model. We carry out standard back testing procedure to validate Regime Switching FIGARCH VaR based forecasts, on S\&P 500 and SHSZ 300 data in 1 minute and 5 minute frequencies. In the Chapter 1, Regime Switching model , and parameter estimation steps based on truncated ARCH infinite and Hamilton filter will be given. Topics like stationary conditions of RS-FIGARCH and standard Normal Tempered Stable distributions as fat-tailed innovations of time series are also covered. In Chapter 2, Fractionally Integrated GARCH is reviewed, and incorporated with Regime switching model. Modified likelihood ratio based test proposed by \cite{Kasahara2013} is introduced as test against multiple regimes. Chapter 3 is to discuss VaR-based back testing procedure, using China's ShanghaiShenzhen 300 Index log return series and S\&P 500 log return series, both in 1 minute and 5 minute frequencies. Backtesing results are given, 99\%, 99.5\% and 99.9\% VaRs are compared with log returns illustratively and violations of Kupiec test at 0.01 and 0.05 significance levels are present as well. We claim that Regime switching FIGARCH not only can be used in risk management but has potential to be used in portfolio optimization. | 86 pages

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.