|
Portfolio Construction with Multivariate
Jan 31, 2001
|
| Abstract: This paper provides an analysis of how the forecasts of the returns of stock indices and their variance can be used for portfolio construction. We estimate a multivariate VAR-GARCH model to predict the monthly returns and the variance matrix of the MSCI North America, MSCI Europe and MSCI Pacific indices from February 1990 until September 1999. We concentrate on the following questions: First, how can forecasts of time series models be used for the selection of portfolio weights? Second, what kind of information improves the portfolio performance? We compare two minimum-variance portfolios, a global portfolio based only on the forecasted variance matrix, and the second portfolio where we forecast the returns and the variance matrix. A comparison based on several criteria between the portfolios and the benchmark shows that multivariate volatility forecasts are useful for active portfolio management since they can beat the benchmark. We use the returns of the MSCI World index in US$ as a benchmark. |
©
2001 Purdue University Last Update: July 9, 2001 Please send comments and suggestions to the Webmaster. |