VaR-implied tail-correlation matrices

Empirical evidence suggests that asset returns correlate more strongly in bear markets than conventional correlation estimates imply. We propose a method for determining complete tail-correlation matrices based on Value-at-Risk (VaR) estimates. We demonstrate how to obtain more effi cient tail-correlation estimates by use of overidenti cation strategies and how to guarantee positive semidefi niteness, a property required for valid risk aggregation and Markowitz-type portfolio optimization. An empirical application to a 30-asset universe illustrates the practical applicability and relevance of the approach in portfolio management.