Modeling the Conditional Covariance Between Stock and Bond Returns: A Multivariate GARCH Approach

Identifying safe haven assets for equity investors through an analysis of the stability of shock transmission

“…Fleming et al, 1998 andScruggs andGlabadanidis (2003) find that the bond market variance is relatively unresponsive to stock return shocks, thereby identifying one appealing characteristic of bonds as a potential safe haven asset. Furthermore De Goeij and Marquering (2004) conclude that there is strong evidence of conditional heteroskedasticity in the covariance matrix of stock and bond market returns and not only variances but also covariances respond asymmetrically to return shocks. Cappiello et al (2006) find evidence of asymmetries in conditional correlations in response to negative returns, with equity exhibiting stronger responses than bonds to joint bad news.…”

“…For example, De Goeij and Marquering (2004) find that the covariance between stocks and bonds tends to be relatively low after bad news in the stock market and good news in the bond market. Connolly et al, 2005 note in their regime-switching analysis that there are two sharply defined regimes.…”

Stock and bond market interactions with level and asymmetry dynamics: An out-of-sample application

“…Most of these models successfully outperform their symmetric counterparts in practice. Furthermore, De Goeij and Marquering (2004) show that the presence of asymmetric e¤ects in conditional covariances is very likely if there exist asymmetric e¤ects in the conditional variances of asset returns. As a portfolio manager's optimal portfolio depends on the predicted covariance between assets, relaxing the symmetric volatility speci…cation leads to superior investment choices.…”

“…In contrast, shocks of opposite signs are much more common in stock and bond returns. De Goeij and Marquering (2004) show that these cross-asymmetric e¤ects are statistically signi…cant in a multivariate GJR (Glosten, Jagannathan and Runkle, 1993) framework, by modeling dynamic interactions between stock and bond returns. 1 Besides the (cross-) asymmetries, another factor which improves the ability to forecast (interest rate) volatility is the level e¤ect.…”

Evaluating portfolio Value-at-Risk using semi-parametric GARCH models

“…Marquering and Verbeek (2004), using simple recursive linear models, analyze the economic value of volatility timing, jointly with return timing, at a monthly frequency. De Goeij and Marquering (2004) examine the economic value of forecasts from a multivariate asymmetric (parametric) GARCH model. These studies limit themselves to the mean-variance framework, where optimal portfolios are determined based on a trade off between the expected return on a portfolio and its variance.…”