Largest entries of sample correlation matrices from equi-correlated normal populations

Jianqing Fan, Tiefeng Jiang

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


The paper studies the limiting distribution of the largest off-diagonal entry of the sample correlation matrices of high-dimensional Gaussian populations with equi-correlation structure. Assume the entries of the population distribution have a common correlation coefficient ρ >0 and both the population dimension p and the sample size n tend to infinity with logp = o(n1/3). As 0<ρ <1, we prove that the largest off-diagonal entry of the sample correlation matrix converges to a Gaussian distribution, and the same is true for the sample covariance matrix as 0<ρ <1/2. This differs substantially from a well-known result for the independent case where ρ = 0, in which the above limiting distribution is an extreme-value distribution. We then study the phase transition between these two limiting distributions and identify the regime of ρ where the transition occurs. If ρ is less than, larger than or is equal to the threshold, the corresponding limiting distribution is the extreme-value distribution, the Gaussian distribution and a convolution of the two distributions, respectively. The proofs rely on a subtle use of the Chen-Stein Poisson approximation method, conditioning, a coupling to create independence and a special property of sample correlation matrices. An application is given for a statistical testing problem.

Original languageEnglish (US)
Pages (from-to)3321-3374
Number of pages54
JournalAnnals of Probability
Issue number5
StatePublished - Sep 1 2019
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


  • Chen-stein poisson approximation
  • Gumbel distribution
  • Maximum sample correlation
  • Multivariate normal distribution
  • Phase transition


Dive into the research topics of 'Largest entries of sample correlation matrices from equi-correlated normal populations'. Together they form a unique fingerprint.

Cite this