(Quantile) Spillover Indexes: Simulation-Based Evidence, Confidence Intervals and a Decomposition

Abstract Quantile spillover indexes have recently become popular for analyzing tail interdependence. Through a simulation study, we show that the estimation of spillover indexes is affected by a positive distortion when the parameters of the fitted models are not evaluated with respect to their statistical significance, or are not estimated subject to regularization. The distortion is reduced for increasing sample sizes, thanks to consistency, or by filtering out nonsignificant parameters, even if in small samples it does not disappear due to type I error. We introduce a simulation-based approach to estimate confidence intervals of quantile spillover indexes. We provide an algebraic decomposition of quantile spillover separating the dynamic interdependence from the contemporaneous interdependence. Empirical evidence on financial companies within the S&P100 index shows that distortions on real data are sizable, and the decomposition highlights the predominance of contemporaneous effects. Our results are confirmed for the Spillover index of Diebold and Yilmaz (2009).