|
Abstract:
|
Value-at-Risk (VaR) of a portfolio is determined by the multivariate distribution of risk factor increments. The RiskMetrics approach, a widely used methodology for VaR estimation, is based on the assumption of multivariate normality. In this study we suggests that the returns are elliptically distributed which better describe the empirical characteristics of financial returns. The distribution of returns will be modeled through copula approach with parameters. The statistical inference will be developed, such as the MLE (maximum likelihood estimator ), IFM (Joe, 1997) etc. The asymptotic efficiency of IFM w.r.t MLE will be derived analytically. The result shows that IFM is an efficient estimator for considered models.
|
