Asymmetric correlation structures and optimal portfolio construction : a copula based approach

Hatherley, Anthony Craig. (2005). Asymmetric correlation structures and optimal portfolio construction : a copula based approach Honours Thesis, School of Business, The University of Queensland.

       
Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
THE19017.pdf Full text application/pdf 8.97MB 5
Author Hatherley, Anthony Craig.
Thesis Title Asymmetric correlation structures and optimal portfolio construction : a copula based approach
School, Centre or Institute School of Business
Institution The University of Queensland
Publication date 2005
Thesis type Honours Thesis
Total pages 151
Language eng
Subjects 15 Commerce, Management, Tourism and Services
Formatted abstract The objective of this thesis is to formally examine the effect that "asymmetric" correlation structures will have on the construction of optimal portfolios and the portfolio decision process. The main contribution of this work to the existing literature is the development of theoretical results highlighting the inability of Mean Variance Portfolio Theory to construct portfolios that adequately meet the investors risk and return requirements when lower tail dependence is present. In particular, this thesis relies on copula functions as a model for asset returns since it can incorporate a broad range of non-normal dependency structures including "fat tails" and tail dependence. Comparing mean-variance and copula derived efficient frontiers; this thesis finds that the optimal portfolio has the potential to differ significantly from the mean-variance portfolio when assets display asymmetric correlation structures. As a result, portfolio return may be increased and diversification improved relative to the mean-variance portfolio when asymmetric correlation is accounted for during the portfolio construction process.

 
Citation counts: Google Scholar Search Google Scholar
Access Statistics: 131 Abstract Views, 5 File Downloads  -  Detailed Statistics
Created: Fri, 19 Nov 2010, 13:01:15 EST by Muhammad Noman Ali on behalf of The University of Queensland Library