High-Dimensional Mahalanobis Distances of Complex Random Vectors
In this paper, we investigate the asymptotic distributions of two types of Mahalanobis distance (MD): leave-one-out MD and classical MD with both Gaussian- and non-Gaussian-distributed complex random vectors, when the sample size <i>n</i> and the dimension of variables <i>p</i&g...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/9/16/1877 |
id |
doaj-274a7b462c7844ebab28286764ddb6a0 |
---|---|
record_format |
Article |
spelling |
doaj-274a7b462c7844ebab28286764ddb6a02021-08-26T14:02:02ZengMDPI AGMathematics2227-73902021-08-0191877187710.3390/math9161877High-Dimensional Mahalanobis Distances of Complex Random VectorsDeliang Dai0Yuli Liang1Department of Economics and Statistics, Linnaeus University, 35195 Växjö, SwedenDepartment of Statistics, Örebro Univeristy, 70281 Örebro, SwedenIn this paper, we investigate the asymptotic distributions of two types of Mahalanobis distance (MD): leave-one-out MD and classical MD with both Gaussian- and non-Gaussian-distributed complex random vectors, when the sample size <i>n</i> and the dimension of variables <i>p</i> increase under a fixed ratio <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>c</mi><mo>=</mo><mi>p</mi><mo>/</mo><mi>n</mi><mo>→</mo><mo>∞</mo></mrow></semantics></math></inline-formula>. We investigate the distributional properties of complex MD when the random samples are independent, but not necessarily identically distributed. Some results regarding the F-matrix <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="bold-italic">F</mi><mo>=</mo><msubsup><mi mathvariant="bold-italic">S</mi><mn>2</mn><mrow><mo>−</mo><mn>1</mn></mrow></msubsup><msub><mi mathvariant="bold-italic">S</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula>—the product of a sample covariance matrix <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>1</mn></msub></semantics></math></inline-formula> (from the independent variable array <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi mathvariant="bold-italic">b</mi><mi>e</mi><msub><mrow><mo>(</mo><msub><mi>Z</mi><mi>i</mi></msub><mo>)</mo></mrow><mrow><mn>1</mn><mo>×</mo><mi>n</mi></mrow></msub></mrow></semantics></math></inline-formula>) with the inverse of another covariance matrix <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>2</mn></msub></semantics></math></inline-formula> (from the independent variable array <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mo>(</mo><msub><mi mathvariant="bold-italic">Z</mi><mrow><mi>j</mi><mo>≠</mo><mi>i</mi></mrow></msub><mo>)</mo></mrow><mrow><mi>p</mi><mo>×</mo><mi>n</mi></mrow></msub></semantics></math></inline-formula>)—are used to develop the asymptotic distributions of MDs. We generalize the F-matrix results so that the independence between the two components <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>1</mn></msub></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>2</mn></msub></semantics></math></inline-formula> of the F-matrix is not required.https://www.mdpi.com/2227-7390/9/16/1877Mahalanobis distancecomplex random vectormoments of MDs |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Deliang Dai Yuli Liang |
spellingShingle |
Deliang Dai Yuli Liang High-Dimensional Mahalanobis Distances of Complex Random Vectors Mathematics Mahalanobis distance complex random vector moments of MDs |
author_facet |
Deliang Dai Yuli Liang |
author_sort |
Deliang Dai |
title |
High-Dimensional Mahalanobis Distances of Complex Random Vectors |
title_short |
High-Dimensional Mahalanobis Distances of Complex Random Vectors |
title_full |
High-Dimensional Mahalanobis Distances of Complex Random Vectors |
title_fullStr |
High-Dimensional Mahalanobis Distances of Complex Random Vectors |
title_full_unstemmed |
High-Dimensional Mahalanobis Distances of Complex Random Vectors |
title_sort |
high-dimensional mahalanobis distances of complex random vectors |
publisher |
MDPI AG |
series |
Mathematics |
issn |
2227-7390 |
publishDate |
2021-08-01 |
description |
In this paper, we investigate the asymptotic distributions of two types of Mahalanobis distance (MD): leave-one-out MD and classical MD with both Gaussian- and non-Gaussian-distributed complex random vectors, when the sample size <i>n</i> and the dimension of variables <i>p</i> increase under a fixed ratio <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>c</mi><mo>=</mo><mi>p</mi><mo>/</mo><mi>n</mi><mo>→</mo><mo>∞</mo></mrow></semantics></math></inline-formula>. We investigate the distributional properties of complex MD when the random samples are independent, but not necessarily identically distributed. Some results regarding the F-matrix <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="bold-italic">F</mi><mo>=</mo><msubsup><mi mathvariant="bold-italic">S</mi><mn>2</mn><mrow><mo>−</mo><mn>1</mn></mrow></msubsup><msub><mi mathvariant="bold-italic">S</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula>—the product of a sample covariance matrix <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>1</mn></msub></semantics></math></inline-formula> (from the independent variable array <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi mathvariant="bold-italic">b</mi><mi>e</mi><msub><mrow><mo>(</mo><msub><mi>Z</mi><mi>i</mi></msub><mo>)</mo></mrow><mrow><mn>1</mn><mo>×</mo><mi>n</mi></mrow></msub></mrow></semantics></math></inline-formula>) with the inverse of another covariance matrix <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>2</mn></msub></semantics></math></inline-formula> (from the independent variable array <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow><mo>(</mo><msub><mi mathvariant="bold-italic">Z</mi><mrow><mi>j</mi><mo>≠</mo><mi>i</mi></mrow></msub><mo>)</mo></mrow><mrow><mi>p</mi><mo>×</mo><mi>n</mi></mrow></msub></semantics></math></inline-formula>)—are used to develop the asymptotic distributions of MDs. We generalize the F-matrix results so that the independence between the two components <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>1</mn></msub></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi mathvariant="bold-italic">S</mi><mn>2</mn></msub></semantics></math></inline-formula> of the F-matrix is not required. |
topic |
Mahalanobis distance complex random vector moments of MDs |
url |
https://www.mdpi.com/2227-7390/9/16/1877 |
work_keys_str_mv |
AT deliangdai highdimensionalmahalanobisdistancesofcomplexrandomvectors AT yuliliang highdimensionalmahalanobisdistancesofcomplexrandomvectors |
_version_ |
1721191790752563200 |