In order to investigate the dependence among assets, markets and sectors, in a flexible way and outgoing correlation parameters, the application of multivariate copula functions can be suggested to bypass or integrate the multivariate GARCH model. Besides, it is widely accepted that financial volatilities move together over time across assets and markets. For these reasons, a new dynamic multivariate model is proposed, defined “time-varying vine copulas”, based on a decomposition of the d-dimensional density into a cascade of bivariate conditional and unconditional copulas, with two desirable features: a flexible construction, which allows for the free specification of d(d-1)/2 copulas, and an easy computation in presence of high dimensional data.
Time varying vine copulas
RIVIECCIO, GIORGIA
2011-01-01
Abstract
In order to investigate the dependence among assets, markets and sectors, in a flexible way and outgoing correlation parameters, the application of multivariate copula functions can be suggested to bypass or integrate the multivariate GARCH model. Besides, it is widely accepted that financial volatilities move together over time across assets and markets. For these reasons, a new dynamic multivariate model is proposed, defined “time-varying vine copulas”, based on a decomposition of the d-dimensional density into a cascade of bivariate conditional and unconditional copulas, with two desirable features: a flexible construction, which allows for the free specification of d(d-1)/2 copulas, and an easy computation in presence of high dimensional data.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
