Please use this identifier to cite or link to this item:
|Title:||The Variance Gamma (VG) Model with Long Range Dependence|
|Keywords:||Variance Gamma (VG) model, t model, subordinator model, long range dependence, self similarity, activity time, financial data|
|Publisher:||University of Sydney.|
School of Mathematics and Statistics
|Abstract:||This thesis mainly builds on the Variance Gamma (VG) model for financial assets over time of Madan & Seneta (1990) and Madan, Carr & Chang (1998), although the model based on the t distribution championed in Heyde & Leonenko (2005) is also given attention. The primary contribution of the thesis is the development of VG models, and the extension of t models, which accommodate a dependence structure in asset price returns. In particular it has become increasingly clear that while returns (log price increments) of historical financial asset time series appear as a reasonable approximation of independent and identically distributed data, squared and absolute returns do not. In fact squared and absolute returns show evidence of being long range dependent through time, with autocorrelation functions that are still significant after 50 to 100 lags. Given this evidence against the assumption of independent returns, it is important that models for financial assets be able to accommodate a dependence structure.|
|Description:||Doctor of Philosophy (PhD)|
|Rights and Permissions:||The author retains copyright of this thesis.|
|Type of Work:||PhD Doctorate|
|Appears in Collections:||Sydney Digital Theses (Open Access)|
This work is protected by Copyright. All rights reserved. Access to this work is provided for the purposes of personal research and study. Except where permitted under the Copyright Act 1968, this work must not be copied or communicated to others without the express permission of the copyright owner. Use the persistent URI in this record to enable others to access this work.
|Finlay(2009).pdf||799.08 kB||Adobe PDF||View/Open|
Items in Sydney eScholarship Repository are protected by copyright, with all rights reserved, unless otherwise indicated.