High-dimensional CLTs for individual Mahalanobis distances

Thomas Holgersson () and Deliang Dai
Additional contact information
Thomas Holgersson: Linnaeus university, Jönköping university, & Centre of Excellence for Science and Innovation Studies (CESIS), Postal: SE 551 11, , Jönköping, , Sweden

No 361, Working Paper Series in Economics and Institutions of Innovation from Royal Institute of Technology, CESIS - Centre of Excellence for Science and Innovation Studies

Abstract: In this paper we derive central limit theorems for two different types of Mahalanobis distances in situations where the dimension of the parent variable increases proportionally with the sample size. It is shown that although the two estimators are closely related and behave similarly in nite dimensions, they have different convergence rates and are also centred at two different points in high-dimensional settings. The limiting distributions are shown to be valid under some general moment conditions and hence available in a wide range of applications.

Keywords: Mahalanobis distance; increasing dimension; weak convergence; Marcenko-Pastur distribution; outliers; Pearson family (search for similar items in EconPapers)
JEL-codes: C38 C46 C50 (search for similar items in EconPapers)
Pages: 13 pages
Date: 2014-05-06
New Economics Papers: this item is included in nep-ecm
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://static.sys.kth.se/itm/wp/cesis/cesiswp361.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hhs:cesisp:0361

Access Statistics for this paper

More papers in Working Paper Series in Economics and Institutions of Innovation from Royal Institute of Technology, CESIS - Centre of Excellence for Science and Innovation Studies CESIS - Centre of Excellence for Science and Innovation Studies, Royal Institute of Technology, SE-100 44 Stockholm, Sweden. Contact information at EDIRC.
Bibliographic data for series maintained by Vardan Hovsepyan ().