EconBase
← All papers

Correlation Matrices in High Dimensions: The Elliptope as a Sample-Correlation Ensemble

Peter Reinhard Hansen

arXiv 4 Aug 2026 · Mathematics — Probability

arXiv:2608.04162 · PDF · Extracted main text

Abstract

The set of $n\times n$ correlation matrices, known as the elliptope, has volume decaying at the super-exponential rate $\exp{-\tfrac14 n^2\log n}$. We characterize where this vanishing volume concentrates. A uniform draw is entrywise close to the identity yet globally far from it and nearly singular: its maximum absolute correlation is of order $\sqrt{\log n/n}$, its Frobenius distance is asymptotic to $\sqrt n$, its empirical spectral distribution converges to the Marchenko-Pastur law with ratio one, and its smallest eigenvalue has the exact $\operatorname{Beta}(1,d)$ distribution, where $d=n(n-1)/2$, and is therefore of order $n^{-2}$. More generally, distinct off-diagonal entries are exactly pairwise independent under every $\operatorname{LKJ}(η)$ law. For the uniform law, this yields a Chen-Stein proof of the extreme-correlation point-process limit and an $O(n^{-1})$ total-variation bound for finite-dimensional exceedance counts relative to Poisson laws with their exact finite-$n$ means. We also identify two distinct scales: $η_n\asymp n$ alters the limiting spectrum, whereas $η_n\asymp n^2$ is needed to keep the Frobenius distance bounded. Finally, for a bounded, centered i.i.d. off-diagonal specification, projection to the nearest correlation matrix incurs a squared repair cost asymptotically at least one-half of the squared Frobenius norm of its off-diagonal part.

Citation extraction

32
references
88
in-text mentions
32
distinct cited
2
self-citations
9,861
main-text words

appendix boundary found by appendix_command · 51% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Daniel Lewandowski, Dorota Kurowicka, and Harry Joe (2009) Generating random correlation matrices based on vines and extended onion method0.9416483%
2Ilya Archakov and Peter Reinhard Hansen (2021) A new parametrization of correlation matrices self0.92843100%
3Harry Joe (2006) Generating random correlation matrices based on partial correlations0.8558662%
4Johannes Heiny, Thomas Mikosch, and Jorge Yslas (2021) Point process convergence for the off-diagonal entries of sample covariance matrices0.84333100%
5Anca M. Hanea and Gabriela F. Nane (2018) The asymptotic distribution of the determinant of a random correlation matrix0.7946350%
6C. R. Johnson and G. Nvdal (1998) The probability that a (partial) matrix is positive semidefinite0.7373367%
7Walter Böhm and Kurt Hornik (2014) Generating random correlation matrices by the simple rejection method: Why it does not work0.73732100%
8Tiefeng Jiang (2004) The limiting distributions of eigenvalues of sample correlation matrices0.6444250%
9Ilya Archakov, Peter Reinhard Hansen, and Yiyao Luo (2024) A new method for generating random correlation matrices self0.64422100%
10John Barnard, Robert McCulloch, and Xiao-Li Meng (2000) Modeling covariance matrices in terms of standard deviations and correlations, with application to shrinkage0.64422100%

Showing the top 10 of 32 scored citations.