Copula goodness-of-fit testing: an overview and power comparison

By Daniel Berg. 2009

317 citations recorded by the source corpus.

Subfields: Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/39b5d493b32d019397789e7085ec3f00cb54d73d

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 Statistics and Probability

Citations in the corpus

FAST LARGE-SAMPLE GOODNESS-OF-FIT TESTS FOR COPULAS (2011, unknown): “The large scale simulations carried out by Genest, Rémillard, and Beaudoin (2009) and Berg (2009) suggest that, overall, this procedure yields the most powerful blanket goodness-of-fit test for copula models. The main inconvenience of this approach is its high computational cost as each parametric b”
Risk management with high-dimensional vine copulas: An analysis of the Euro Stoxx 50 (2013, methodology): “…(Breymann et al. 2003) to investigate the hypothesis of joint normality, since this test performs particularly well against heavy tailed alternatives, as they often occur in financial applications (Berg 2009), and since it is computationally less demanding than alternative multivariate tests.”
Truncated regular vines in high dimensions with application to financial data (2012, methodology): “The first-mentioned test was shown to perform very well in the studies Berg (2009) and Genest et al.”
Maximum likelihood estimation of mixed C-vines with application to exchange rates (2012, methodology): “(2006) and Berg (2009). One recommended test is based on the Cramér-von-Mises statistics, which we will utilize later.”
A Goodness-of-fit Test for Copulas (2014, methodology): “, 2009; Berg, 2009 for recent surveys). However, only a few are “blanket.” For example, Klugman and Parsa (1999) propose tests that involve ad hoc categorization of the data; Fermanian (2005) and Scaillet (2007) propose tests that are based on kernels and weight functions and use the associated smoo”
Models for construction of multivariate dependence – a comparison study (2009, background): “Berg (2007) for an overview and power comparison.”
Pair-copulas modeling in finance (2010, methodology): “(2006), the PIT algorithm (Rosenblatt, 1952), Berg & Bakken (2006). It seems that the most accepted idea is to transform the data into a set of independent and standard uniform variables, and to calculate some measure of distance, such as the Anderson-Darling or the Kolmogorov-Smirnov distance betwe”
Bivariate Flood Frequency Analysis with Historical Information Based on Copula (2013, methodology): “The ability of Gumbel family to model the available bivariate data was checked through robust multivariate goodness-of-fit tests (Genest et al. 2009; Berg 2009); the resulting large P-values (shown in Fig.”
Modeling Multivariate Distributions with Continuous Margins Using the copula R Package (2010, result): “In the large scale Monte Carlo experiments carried out by Berg (2009) and Genest, R´emillard, and Beaudoin (2009b), the statistic gave the best results overall.”
Copula-GARCH versus dynamic conditional correlation: an empirical study on VaR and ES forecasting accuracy (2013, methodology): “As stated by Berg (2009), Rosenblatt’s transform can be used for multivariate GoF tests by applying it to a random sample, assuming a parametric null hypothesis copula.”
A review of copula models for economic time series (2012, methodology): “Across a range of data generating processes, they conclude that a Cramér–von Mises test (applied to the empirical copula or to the Rosenblatt transform of the original data) is the most powerful, a finding that is supported by Berg [14] who considers some further tests.”
Copula Methods for Forecasting Multivariate Time Series (2013, methodology): “…Mises test (applied to the empirical copula or to the Rosenblatt transform of the original data) is the most powerful, a nding that is supported by Berg (2009) who considers some further tests. where C2j1;t is the conditional distribution of U2tjU1t: In general multivariate applications, the…”