Goodness-of-fit test for copulas
β Scribed by Valentyn Panchenko
- Publisher
- Elsevier Science
- Year
- 2005
- Tongue
- English
- Weight
- 195 KB
- Volume
- 355
- Category
- Article
- ISSN
- 0378-4371
No coin nor oath required. For personal study only.
β¦ Synopsis
Copulas are often used in finance to characterize the dependence between assets. However, a choice of the functional form for the copula is an open question in the literature. This paper develops a goodness-of-fit test for copulas based on positive definite bilinear forms. The suggested test avoids the use of plug-in estimators that is the common practice in the literature. The test statistics can be consistently computed on the basis of V-estimators even in the case of large dimensions. The test is applied to a dataset of US large cap stocks to assess the performance of the Gaussian copula for the portfolios of assets of various dimension. The Gaussian copula appears to be inadequate to characterize the dependence between assets.
π SIMILAR VOLUMES
A \(p \times 1\) random vector \(\mathbf{x}\) is said to have a spherical distribution, if for every \(p \times p\) orthogonal matrix \(\mathbf{Q}, \mathbf{x}\) and \(\mathbf{Q x}\) have the same distribution. In this paper, some nonparametric goodness of rit Wilcoxon-type tests for sphericity are p
The copula of a bivariate distribution, constructed by making marginal transformations of each component, captures all the information in the bivariate distribution about the dependence between two variables. For frailty models for bivariate data the choice of a family of distributions for the rando