Please use this identifier to cite or link to this item: http://cmuir.cmu.ac.th/jspui/handle/6653943832/71867
Title: Risk, Return, and Portfolio Optimization for Various Industries Based on Mixed Copula Approach
Authors: Sukrit Thongkairat
Woraphon Yamaka
Authors: Sukrit Thongkairat
Woraphon Yamaka
Keywords: Computer Science
Issue Date: 1-Jan-2021
Abstract: © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. This study aims to apply the concept of mixed copula to the problem of finding the risk, return, and portfolio diversification at the industry level in the stock markets of Thailand and Vietnam. Six industry indices are considered in this study. Prior to constructing the portfolio, we compare the mixed copula with the traditional copula to show the better performance of the mixed copula in terms of the lower AIC and BIC. The empirical results show that the mixed Student-t and Clayton copula model can capture the dependence structure of the portfolio returns much better than the traditional model. Then, we apply the best-fit model to do the Monte Carlo simulation for constructing the efficiency frontier and find the optimal investment combination from five portfolio optimization approaches including Uniform portfolio, Global Minimum Variance Portfolio (GMVP), Markowitz portfolio, Maximum Sharpe ratio portfolio, and Long-Short quintile. The findings suggest that, overall, the industry index of Vietnam and the consumer services index of Thailand should be given primary attention because they exhibit the highest performance compared to other industries in the stock markets. This suggestion is supported by the results of the Maximum Sharpe ratio portfolio (the best portfolio optimization approach) that assign the largest portfolio allocation to the industry sector for Vietnam and the consumer services sector for Thailand.
URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85096222793&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/71867
ISSN: 18609503
1860949X
Appears in Collections:CMUL: Journal Articles

Files in This Item:
There are no files associated with this item.


Items in CMUIR are protected by copyright, with all rights reserved, unless otherwise indicated.