Search Results - subject:"Canonical Maximum-Likelihood"

Forecasting portfolio-Value-at-Risk with nonparametric lower tail dependence estimates

Siburg, Karl Friedrich; Stoimenov, Pavel; Weiß, Gregor N.F. - In: Journal of Banking & Finance 54 (2015) C, pp. 129-140

-GARCH model where the parameter of a Clayton copula is estimated via Canonical Maximum-Likelihood. The superiority of our proposed …

Persistent link: https://www.econbiz.de/10011264647

Forecasting portfolio-Value-at-Risk with nonparametric lower tail dependence estimates

Siburg, Karl Friedrich; Stoimenov, Pavel; Weiß, Gregor - In: Journal of banking & finance 54 (2015), pp. 129-140

Persistent link: https://www.econbiz.de/10011377805

Independent component analysis via copula techniques

Chen, Ray-Bing; Guo, Meihui; Härdle, Wolfgang Karl; … - 2008

Independent component analysis (ICA) is a modern factor analysis tool developed in the last two decades. Given p-dimensional data, we search for that linear combination of data which creates (almost) independent components. Here copulae are used to model the p-dimensional data and then...

Persistent link: https://www.econbiz.de/10010274138

Independent Component Analysis Via Copula Techniques

Chen, Ray-Bing; Guo, Meihui; Härdle, Wolfgang; Huang, … - Sonderforschungsbereich 649: Ökonomisches Risiko, … - 2008

the advantages of this method. Key words: Blind source separation, Canonical maximum likelihood method, Givens rotation … divergence functions, oi(^ i). Here canonical maximum likelihood (CML) method is adopted to esti- mate the copula parameter. The … copula. Both parameters are all estimated by canonical maximum likelihood method. As mentioned before, we need to white the …

Persistent link: https://www.econbiz.de/10005677950