Comparison of semiparametric and parametric methods for estimating copulas

By Gunky Kim, Mervyn J. Silvapulle, P. Silvapulle. Computational Statistics & Data Analysis, 2007

364 citations recorded by the source corpus.

Subfields: Finance, Global and Planetary Change, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/ac1278605e333492ffe12a4e357f3feb3a7b4764

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Finance

In Global and Planetary Change

In Statistics and Probability

Citations in the corpus

Bayesian inference for multivariate copulas using pair-copula constructions. (2010, methodology): “We illustrate this first with Kendall’s τ (see Kruskal (1958)) which is an alternative dependence measure to the linear correlation coefficient .”
Simulated Method of Moments Estimation for Copula-Based Multivariate Models (2013, neutral): “…correctly specified, this improves the efficiency of the estimator relative to the proposed SMM approach; however, it introduces the possibility of misspecified marginal distributions, which can have deleterious effects on the copula parameter estimates (see Kim, Silvapulle, and Silvapulle 2007).”
Analysis of directional dependence using asymmetric copula-based regression models (2014, methodology): “[19] indicates that the ML and IFM methods are nonrobust against misspecification of the marginals.”
Pair‐copula constructions for non‐Gaussian DAG models (2012, background): “(2006) and Kurowicka and Cooke (2006). We follow these authors’ approach of utilising PCCs to specifically construct non-Gaussian distributions in order to capture features such as tail behaviour and non-linear, asymmetric dependence.”
Modeling Multivariate Distributions with Continuous Margins Using the copula R Package (2010, background): “…makes the estimation of C margin-free, which implies that a misspeciﬁcation of one of the marginals F 1 , . . . , F d will have no consequences on the copula estimate (see e.g., Fermanian and Scaillet 2005; Kim, Silvapulle, and Silvapulle 2007, for empirical arguments in favor of the use of ranks).”
Bayesian model selection for D‐vine pair‐copula constructions (2011, background): “Thus Kim, Silvapulle, and Silvapulle (2007) have shown that a separate estimation of the marginal parameters may have an essential influence on the parameter estimation of multivariate copulas.”
Everything You Always Wanted to Know about Copula Modeling but Were Afraid to Ask (2007, methodology): “Although they usually perform well, the estimates of the association parameters derived by the IFM technique clearly depend on the choice of F and G, and thus always run the risk of being unduly affected if the models selected for the margins turn out to be inappropriate see e.g., Kim et al. 2007 .”
Copulas: A Personal View (2009, neutral): “Maximum Likelihood approach; see for instance Kim et al. [ 28 ].”
A Primer on Copulas for Count Data (2007, methodology): “This approach is generally preferred in practice because in addition to being reasonably efficient, the resulting estimator for q is rank-based and hence robust to the misspecification of the marginal distributions, as recently illustrated by Kim et al. (2007).”
Parameter estimation for pair-copula constructions (2013, background): “[27], have demonstrated that unless the dependence between the variables is extreme, this loss tends to be rather small.”