Optimal Diversification within Mixed-Asset Portfolios using a Conditional Heteroskedasticity Approach: Evidence from the U.S. and the U.K.
JPMorgan Asset Management
Lombard Odier & Cie; VU University Amsterdam
University of Geneva - Graduate School of Business (HEC-Geneva); University of Aberdeen - Business School; Swiss Finance Institute
University of Aberdeen - Centre for Property Research
Journal of Real Estate Portfolio Management, Vol. 5, No. 1, April 1999
In this article, portfolio allocation strategies based on a threshold autoregressive conditional heteroskedasticity model (QTARCH) are constructed for the United States and the United Kingdom and compared to a conventional asset allocation. Our procedure is based on partitioning the historical data into 'states of the world,' which are used to produce expectations of return and risk. Several approaches are developed to partition an initial in-sample period (1978?1983), using quarterly asset returns and economic data. These partitions are then used to test out-of-sample strategies for the next quarter. Although the conditional results are sensitive to the method of partitioning, we show that the approach can improve portfolio performance in both countries and that most of the performance improvement stems from using conditional variances-covariances.
JEL Classification: G12Accepted Paper Series
Date posted: April 16, 1999
© 2013 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollo2 in 0.312 seconds