Sequential conditional correlations: Inference and evaluation

Abstract

This paper presents a new approach to the modeling of conditional correlation matrices within the multivariate GARCH framework. The procedure, which consists in breaking the matrix into the product of a sequence of matrices with desirable characteristics, in effect converts a highly dimensional and intractable optimization problem into a series of simple and feasible estimations. This in turn allows for richer parameterizations and complex functional forms for the single components. An empirical application involving the conditional second moments of 69 selected stocks from the NASDAQ100 shows how the new procedure results in strikingly accurate measures of the conditional correlations.

International stock markets interactions and conditional correlations

“…Under the DCC specification, the correlation is time varying and is able to capture the changes over time. For further details about various multivariate models, refer to Bauwens et al (2006), and Palandri (2005).…”

Do negative and positive equity returns share the same volatility dynamics?

“…However, for large K the models' predictions and the realized measures converge to the unconditional variances giving the misleading impression that the competing models perform equally well. This is not the case for the periods considered: K ¼ 120 strikes the largest differences in models' performance signaling both a significant variance reduction and a negligible bias which would make the models look the same (for a detailed discussion see Palandri (2009)). Therefore, throughout the rest of the paper, the empirical findings are presented and discussed for K ¼ 120.…”

MGARCH models: Trade-off between feasibility and flexibility

“…Consequently, the asymptotic covariance matrix of the parameter estimator, computed as the average of the T outer-products of the score, will not be full rank for large N . This is a feature inherent to all MGARCH models and all their estimators; see Palandri (2009).…”