Dependent conditional value-at-risk for aggregate risk models

Risk measure forecast and model have been developed in order to not only provide better but also preserve its (empirical) property especially coherent property. Whilst the widely used risk of Value-at-Risk (VaR) has shown performance benefit many applications, it is fact a measure. Conditional VaR (CoVaR), defined as mean losses beyond VaR, one alternative measures that satisfies There several extensions CoVaR such Modified (MCoVaR) Copula (CCoVaR). In this paper, we propose another measure, called Dependent (DCoVaR), for target loss depends on random loss, including parameter treated loss. It found our DCoVaR provides than both MCoVaR CCoVaR. Numerical simulation carried out illustrate proposed DCoVaR. addition, do an empirical study financial returns data compute heteroscedastic process GARCH(1,1). The results show Gumbel describes dependence structure quite nicely using more accurate Clayton Copula. superior MCoVaR, CCoVaR comprehend connection between bivariate help us exceedingly about how optimum position investments elevate protection. other words, putting suggested will enable avoid non-essential extra capital allocation while neglecting risks associated with risk. Moreover, actuarial context, can be applied determine insurance premiums reducing company.