 Applications on linear spectral statistics of high-dimensional sample covariance matrix with divergent spectrumYangchun Zhang, Yirui Zhou and Xiaowei Liu Computational Statistics & Data Analysis, 2023, vol. 178, issue C Abstract: In large-scale statistical inference when the sample size n and dimension p both tend to infinity, the original central limit theorems (CLTs) produce the bounded spectral norm assumption of the covariance matrix which excludes many important applications. Recently, a new CLT (DCLT) was established for the unbounded population spectrum, allowing utilization with divergent spectral norm population models. Comparative simulations are provided in this study for the original CLT and DCLT, and applications for John's test, interval estimation, and point estimation. Numerical results document the greater performance of DCLT than the original CLT in most cases. Moreover, for the bounded population spectrum, the DCLT modifies the limiting mean and variance shift, and gains preferable theoretical results with small p and n. Real data implementation are illustrated on a radio frequency dataset. Keywords: Spiked population model; Random matrix theory; Population spectral distribution (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:csdana:v:178:y:2023:i:c:s0167947322001979 DOI: 10.1016/j.csda.2022.107617 Access Statistics for this article Computational Statistics & Data Analysis is currently edited by S.P. Azen More articles in Computational Statistics & Data Analysis from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.