Refined Measures Of Dynamic Connectedness Based On Time-Varying Parameter Vector Autoregressions
Sprache des Vortragstitels:
12th International Conference On Computational And Financial Econometrics
Sprache des Tagungstitel:
In this study, we combine the dynamic connectedness measures originally introduced by Diebold and Y?lmaz (2014) with a time-varying parameter vector autoregressive model (TVP-VAR) with a time-varying variance-covariance structure. This framework allows to capture possible changes in the underlying structure of the data in a more flexible and robust manner. Specifically, there is neither need to arbitrarily set the rolling-window size nor a loss of observations in the calculation of the dynamic measures of connectedness as no rolling-window analysis is involved. Since this TVP-VAR framework rests on a multivariate Kalman Filter approach it is less sensitive to outliers than the traditionally rolling-window approach. Furthermore, we illustrate those merits by conducting various Monte Carlo simulations. Moreover, we are investigating the dynamic connectedness measures of the four most traded foreign exchange rates by comparing the TVP-VAR results with three different window- sized rolling-window VARs. Finally, we propose uncertainty measures for TVP-VAR-based and rolling-window VAR-based dynamic connectedness measures.