Generating random correlation matrices based on vines and extended onion method

By D. Lewandowski, Dorota Kurowicka, Harry Joe. 2009

1,052 citations recorded by the source corpus.

Subfields: Geometry and Topology, Nature and Landscape Conservation, Statistics and Probability

How researchers see this paper

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

In Geometry and Topology

In Nature and Landscape Conservation

In Statistics and Probability

Citations in the corpus

Metalearners for estimating heterogeneous treatment effects using machine learning (2017, background): “[33] Lewandowski D, Kurowicka D, Joe H (2009) Generating random correlation matrices based on vines and extended onion method.”
A method for generating realistic correlation matrices (2011, background): “Although there 9 has been additional work expanding the ideas associated with generating random cor10 relation matrices [8, 16, 21, 28, 35] and even randomly generating correlation matrices 11 within particular settings [15, 33], to our knowledge there is no literature devoted to 12 the problem of a”
Maximum likelihood estimation of skew-t copulas with its applications to stock returns (2018, background): “, d + 1, where ρij;1:(j−1) is the partial correlation between ith variate and jth one with first to (j − 1)th variates held constant [8,28].”
Foundations of Stated Preference Elicitation: Consumer Behavior and Choice-based Conjoint Analysis (2019, background): “…normal prior for μ, relatively diffuse exponential densities for the elements of D, and a LKJ(1) density for the correlation matrix ΓΓ’; see Lewandowski, Kurowicka, and Joe (2009).33 Terminal Steps: Consider sampler data μi, Ωi, and vni for subjects n = 1,..,N and iterations i = 1,..,I…”
brms: An R Package for Bayesian Multilevel Models Using Stan (2017, methodology): “For Ω k , we use the LKJ-Correlation prior with parameter ζ > 0 by Lewandowski, Kurowicka, and Joe (2009) 1 : The expected value of the LKJ-prior is the identity matrix (implying correlations of zero) for any positive value of ζ , which can be interpreted like the shape parameter of a symmetric…”
A parametric texture model based on deep convolutional features closely matches texture appearance for humans (2017, methodology): “Finally, we set a prior over the correlation matrix for observer and image-level o ﬀ sets in the ﬁxed e ﬀ ects that assumes that smaller correlations are slightly more likely than larger ones (an “ lkj(2) ” prior, see Lewandowski, Kurowicka, and Joe (2009); Stan Development Team (2015) for details).”
Pair-Copula Constructions of Multivariate Copulas (2010, background): “Random generation of correlation matrices are considered in [33] using D-vines and more general using regular vines in [42].”