Namespaces
Variants
Actions

Difference between revisions of "Matrix variate elliptically contoured distribution"

From Encyclopedia of Mathematics
Jump to: navigation, search
(Importing text file)
 
(latex details)
 
(One intermediate revision by one other user not shown)
Line 1: Line 1:
 +
<!--This article has been texified automatically. Since there was no Nroff source code for this article,
 +
the semi-automatic procedure described at https://encyclopediaofmath.org/wiki/User:Maximilian_Janisch/latexlist
 +
was used.
 +
If the TeX and formula formatting is correct, please remove this message and the {{TEX|semi-auto}} category.
 +
 +
Out of 69 formulas, 69 were replaced by TEX code.-->
 +
 +
{{TEX|semi-auto}}{{TEX|done}}
 
The class of matrix variate elliptically contoured distributions can be defined in many ways. Here the definition of A.K. Gupta and T. Varga [[#References|[a4]]] is given.
 
The class of matrix variate elliptically contoured distributions can be defined in many ways. Here the definition of A.K. Gupta and T. Varga [[#References|[a4]]] is given.
  
A random matrix <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201601.png" /> (see [[Matrix variate distribution|Matrix variate distribution]]) is said to have a matrix variate elliptically contoured distribution if its [[Characteristic function|characteristic function]] has the form <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201602.png" /> with <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201603.png" /> a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201604.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201605.png" /> a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201606.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201607.png" /> a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201608.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m1201609.png" /> a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016010.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016011.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016012.png" /> and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016013.png" />. This distribution is denoted by <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016014.png" />. If the distribution of <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016015.png" /> is absolutely continuous (cf. also [[Absolute continuity|Absolute continuity]]), then its probability density function (cf. also [[Density of a probability distribution|Density of a probability distribution]]) has the form
+
A random matrix $X ( p \times n )$ (see [[Matrix variate distribution|Matrix variate distribution]]) is said to have a matrix variate elliptically contoured distribution if its [[Characteristic function|characteristic function]] has the form $\phi _ { X } ( T ) = \operatorname { etr } ( i T ^ { \prime } M ) \psi ( \operatorname { tr } ( T ^ { \prime } \Sigma T \Phi ) )$ with $T$ a $( p \times n )$-matrix, $M$ a $( p \times n )$-matrix, $\Sigma$ a $( p \times p )$-matrix, $\Phi$ a $( n \times n )$-matrix, $\Sigma \geq 0$, $\Phi \geq 0$ and $\psi : [ 0 , \infty ) \rightarrow \mathbf{R}$. This distribution is denoted by $E _ { p , n } ( M , \Sigma \otimes \Phi , \psi )$. If the distribution of $X$ is absolutely continuous (cf. also [[Absolute continuity|Absolute continuity]]), then its probability density function (cf. also [[Density of a probability distribution|Density of a probability distribution]]) has the form
  
<table class="eq" style="width:100%;"> <tr><td valign="top" style="width:94%;text-align:center;"><img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016016.png" /></td> </tr></table>
+
\begin{equation*} | \Sigma | ^ { - n / 2 } | \Phi | ^ { - p / 2 } h ( \operatorname { tr } \left( ( X - M ) ^ { \prime } \Sigma ^ { - 1 } ( X - M ) \Phi ^ { - 1 } ) \right), \end{equation*}
  
where <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016017.png" /> and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016018.png" /> determine each other.
+
where $h$ and $\psi$ determine each other.
  
An important subclass of the class of matrix variate elliptically contoured distributions is the class of matrix variate normal distributions. A matrix variate elliptically contoured distribution has many properties which are similar to the [[Normal distribution|normal distribution]]. For example, linear functions of a random matrix with a matrix variate elliptically contoured distribution also have elliptically contoured distributions. That is, if <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016019.png" />, then for given constant matrices <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016020.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016021.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016022.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016023.png" />.
+
An important subclass of the class of matrix variate elliptically contoured distributions is the class of matrix variate normal distributions. A matrix variate elliptically contoured distribution has many properties which are similar to the [[Normal distribution|normal distribution]]. For example, linear functions of a random matrix with a matrix variate elliptically contoured distribution also have elliptically contoured distributions. That is, if $X \sim E _ { p , n } ( M , \Sigma \otimes \Phi , \psi )$, then for given constant matrices $C ( q \times n )$, $A ( q \times p )$, $B ( n \times m )$, $A X B + C \sim E _ { q , n } ( A M B + C , ( A \Sigma A ^ { \prime } ) \otimes ( B ^ { \prime } \Phi B ) , \psi )$.
  
If <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016024.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016025.png" /> and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016026.png" /> are partitioned as
+
If $X$, $M$ and $\Sigma$ are partitioned as
  
<table class="eq" style="width:100%;"> <tr><td valign="top" style="width:94%;text-align:center;"><img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016027.png" /></td> </tr></table>
+
\begin{equation*} X = \left( \begin{array} { l } { X _ { 1 } } \\ { X _ { 2 } } \end{array} \right) , M = \left( \begin{array} { c } { M _ { 1 } } \\ { M _ { 2 } } \end{array} \right) , \Sigma = \left( \begin{array} { l l } { \Sigma _ { 11 } } &amp; { \Sigma _ { 12 } } \\ { \Sigma _ { 21 } } &amp; { \Sigma _ { 22 } } \end{array} \right), \end{equation*}
  
where <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016028.png" /> is a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016029.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016030.png" /> is a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016031.png" />-matrix and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016032.png" /> is a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016033.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016034.png" />, then <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016035.png" />. However, if <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016036.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016037.png" /> and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016038.png" /> are partitioned as
+
where $X _ { 1 }$ is a $( q \times n )$-matrix, $M _ { 1 }$ is a $( q \times n )$-matrix and $\Sigma _ { 11 }$ is a $( q \times q )$-matrix, $q < p$, then $X _ { 1 } \sim E _ { q ,\, n } ( M _ { 1 } , \Sigma _ { 11 } \otimes \Phi , \psi )$. However, if $X$, $M$ and $\Phi$ are partitioned as
  
<table class="eq" style="width:100%;"> <tr><td valign="top" style="width:94%;text-align:center;"><img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016039.png" /></td> </tr></table>
+
\begin{equation*} X = ( X _ { 1 } , X _ { 2 } ) , M = ( M _ { 1 } , M _ { 2 } ) , \Phi = \left( \begin{array} { c c } { \Phi _ { 11 } } &amp; { \Phi _ { 12 } } \\ { \Phi _ { 21 } } &amp; { \Phi _ { 22 } } \end{array} \right), \end{equation*}
  
where <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016040.png" /> is a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016041.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016042.png" /> is a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016043.png" />-matrix, and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016044.png" /> is an <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016045.png" />-matrix, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016046.png" />, then <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016047.png" />.
+
where $X _ { 1 }$ is a $( p \times m )$-matrix, $M _ { 1 }$ is a $( p \times m )$-matrix, and $\Phi _ { 11 }$ is an $( m \times m )$-matrix, $m < n$, then $X _ { 1 } \sim E _ { p , m } ( M _ { 1 } , \Sigma \otimes \Phi _ { 11 } , \psi )$.
  
Here, if the expectations exist, then <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016048.png" /> and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016049.png" />, where <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016050.png" />. An important tool in the study of matrix variate elliptically contoured distributions is the stochastic representation of <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016051.png" />:
+
Here, if the expectations exist, then $\mathsf{E} ( X ) = M$ and $\operatorname { cov } ( X ) = c \Sigma \otimes \Phi$, where $c = - 2 \psi ^ { \prime } ( 0 )$. An important tool in the study of matrix variate elliptically contoured distributions is the stochastic representation of $X$:
  
<table class="eq" style="width:100%;"> <tr><td valign="top" style="width:94%;text-align:center;"><img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016052.png" /></td> </tr></table>
+
\begin{equation*} X : = M + r A U B ^ { \prime }, \end{equation*}
  
where <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016053.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016054.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016055.png" /> is a <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016056.png" />-matrix and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016057.png" /> is uniformly distributed on the unit sphere in <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016058.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016059.png" /> is a non-negative [[Random variable|random variable]], <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016060.png" /> and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016061.png" /> are independent, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016062.png" />, and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016063.png" />. Moreover,
+
where $\operatorname{rank} ( \Sigma ) = p _ { 1 }$, $\operatorname{rank} ( \Phi ) = n _ { 1 }$, $U$ is a $( p _ { 1 } \times n _ { 1 } )$-matrix and $\overset{\rightharpoonup} { f n n m e } ( U ^ { \prime } )$ is uniformly distributed on the unit sphere in $\mathbf{R} ^ { p_1 n_1 }  $, $r$ is a non-negative [[Random variable|random variable]], $r$ and $U$ are independent, $\Sigma = A A ^ { \prime }$, and $\Phi = B B ^ { \prime }$. Moreover,
  
<table class="eq" style="width:100%;"> <tr><td valign="top" style="width:94%;text-align:center;"><img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016064.png" /></td> </tr></table>
+
\begin{equation*} \psi ( u ) = \int _ { 0 } ^ { \infty } \Omega _ { p _ { 1 } n _ { 1 } } ( r ^ { 2 } u ) d F ( r ) , u \geq 0, \end{equation*}
  
where <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016065.png" />, <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016066.png" /> denotes the characteristic function of <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016067.png" />, and <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016068.png" /> denotes the distribution function of <img align="absmiddle" border="0" src="https://www.encyclopediaofmath.org/legacyimages/m/m120/m120160/m12016069.png" />.
+
where $\Omega _ { p _ { 1 } n _ { 1 } } ( t ^ { \prime } t ^ { \prime } )$, $t \in {\bf R} ^ { p _ { 1 } n _ { 1 } }$ denotes the characteristic function of $\overset{\rightharpoonup} { f n n m e } ( U ^ { \prime } )$, and $F ( r )$ denotes the distribution function of $r$.
  
 
====References====
 
====References====
<table><TR><TD valign="top">[a1]</TD> <TD valign="top">  K.T. Fang,  Y.T. Zhang,  "Generalized multivariate analysis" , Springer  (1990)</TD></TR><TR><TD valign="top">[a2]</TD> <TD valign="top">  K.T. Fang,  T.W. Anderson,  "Statistical inference in elliptically contoured and related distributions" , Allerton Press  (1990)</TD></TR><TR><TD valign="top">[a3]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Rank of a quadratic form in an elliptically contoured matrix random variable"  ''Statist. Probab. Lett.'' , '''12'''  (1991)  pp. 131–134</TD></TR><TR><TD valign="top">[a4]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Elliptically contoured models in statistics" , Kluwer Acad. Publ.  (1993)</TD></TR><TR><TD valign="top">[a5]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Some applications of the stochastic representation of elliptically contoured distribution"  ''Random Oper. and Stoch. Eqs.'' , '''2'''  (1994)  pp. 1–11</TD></TR><TR><TD valign="top">[a6]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "A new class of matrix variate elliptically contoured distributions"  ''J. Italian Statist. Soc.'' , '''3'''  (1994)  pp. 255–270</TD></TR><TR><TD valign="top">[a7]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Moments and other expected values for matrix variate elliptically contoured distributions"  ''Statistica'' , '''54'''  (1994)  pp. 361–373</TD></TR><TR><TD valign="top">[a8]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Normal mixture representation of matrix variate elliptically contoured distributions"  ''Sankhyā Ser. A'' , '''57'''  (1995)  pp. 68–78</TD></TR><TR><TD valign="top">[a9]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Some inference problems for matrix variate elliptically contoured distributions"  ''Statistics'' , '''26'''  (1995)  pp. 219–229</TD></TR><TR><TD valign="top">[a10]</TD> <TD valign="top">  A.K. Gupta,  T. Varga,  "Characterization of matrix variate elliptically contoured distributions" , ''Adv. Theory and Practice of Statistics: A Volume in Honor of Samuel Kotz'' , Wiley  (1997)  pp. 455–467</TD></TR></table>
+
<table><tr><td valign="top">[a1]</td> <td valign="top">  K.T. Fang,  Y.T. Zhang,  "Generalized multivariate analysis" , Springer  (1990)</td></tr><tr><td valign="top">[a2]</td> <td valign="top">  K.T. Fang,  T.W. Anderson,  "Statistical inference in elliptically contoured and related distributions" , Allerton Press  (1990)</td></tr><tr><td valign="top">[a3]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Rank of a quadratic form in an elliptically contoured matrix random variable"  ''Statist. Probab. Lett.'' , '''12'''  (1991)  pp. 131–134</td></tr><tr><td valign="top">[a4]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Elliptically contoured models in statistics" , Kluwer Acad. Publ.  (1993)</td></tr><tr><td valign="top">[a5]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Some applications of the stochastic representation of elliptically contoured distribution"  ''Random Oper. and Stoch. Eqs.'' , '''2'''  (1994)  pp. 1–11</td></tr><tr><td valign="top">[a6]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "A new class of matrix variate elliptically contoured distributions"  ''J. Italian Statist. Soc.'' , '''3'''  (1994)  pp. 255–270</td></tr><tr><td valign="top">[a7]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Moments and other expected values for matrix variate elliptically contoured distributions"  ''Statistica'' , '''54'''  (1994)  pp. 361–373</td></tr><tr><td valign="top">[a8]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Normal mixture representation of matrix variate elliptically contoured distributions"  ''Sankhyā Ser. A'' , '''57'''  (1995)  pp. 68–78</td></tr><tr><td valign="top">[a9]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Some inference problems for matrix variate elliptically contoured distributions"  ''Statistics'' , '''26'''  (1995)  pp. 219–229</td></tr><tr><td valign="top">[a10]</td> <td valign="top">  A.K. Gupta,  T. Varga,  "Characterization of matrix variate elliptically contoured distributions" , ''Adv. Theory and Practice of Statistics: A Volume in Honor of Samuel Kotz'' , Wiley  (1997)  pp. 455–467</td></tr></table>

Latest revision as of 07:26, 28 January 2024

The class of matrix variate elliptically contoured distributions can be defined in many ways. Here the definition of A.K. Gupta and T. Varga [a4] is given.

A random matrix $X ( p \times n )$ (see Matrix variate distribution) is said to have a matrix variate elliptically contoured distribution if its characteristic function has the form $\phi _ { X } ( T ) = \operatorname { etr } ( i T ^ { \prime } M ) \psi ( \operatorname { tr } ( T ^ { \prime } \Sigma T \Phi ) )$ with $T$ a $( p \times n )$-matrix, $M$ a $( p \times n )$-matrix, $\Sigma$ a $( p \times p )$-matrix, $\Phi$ a $( n \times n )$-matrix, $\Sigma \geq 0$, $\Phi \geq 0$ and $\psi : [ 0 , \infty ) \rightarrow \mathbf{R}$. This distribution is denoted by $E _ { p , n } ( M , \Sigma \otimes \Phi , \psi )$. If the distribution of $X$ is absolutely continuous (cf. also Absolute continuity), then its probability density function (cf. also Density of a probability distribution) has the form

\begin{equation*} | \Sigma | ^ { - n / 2 } | \Phi | ^ { - p / 2 } h ( \operatorname { tr } \left( ( X - M ) ^ { \prime } \Sigma ^ { - 1 } ( X - M ) \Phi ^ { - 1 } ) \right), \end{equation*}

where $h$ and $\psi$ determine each other.

An important subclass of the class of matrix variate elliptically contoured distributions is the class of matrix variate normal distributions. A matrix variate elliptically contoured distribution has many properties which are similar to the normal distribution. For example, linear functions of a random matrix with a matrix variate elliptically contoured distribution also have elliptically contoured distributions. That is, if $X \sim E _ { p , n } ( M , \Sigma \otimes \Phi , \psi )$, then for given constant matrices $C ( q \times n )$, $A ( q \times p )$, $B ( n \times m )$, $A X B + C \sim E _ { q , n } ( A M B + C , ( A \Sigma A ^ { \prime } ) \otimes ( B ^ { \prime } \Phi B ) , \psi )$.

If $X$, $M$ and $\Sigma$ are partitioned as

\begin{equation*} X = \left( \begin{array} { l } { X _ { 1 } } \\ { X _ { 2 } } \end{array} \right) , M = \left( \begin{array} { c } { M _ { 1 } } \\ { M _ { 2 } } \end{array} \right) , \Sigma = \left( \begin{array} { l l } { \Sigma _ { 11 } } & { \Sigma _ { 12 } } \\ { \Sigma _ { 21 } } & { \Sigma _ { 22 } } \end{array} \right), \end{equation*}

where $X _ { 1 }$ is a $( q \times n )$-matrix, $M _ { 1 }$ is a $( q \times n )$-matrix and $\Sigma _ { 11 }$ is a $( q \times q )$-matrix, $q < p$, then $X _ { 1 } \sim E _ { q ,\, n } ( M _ { 1 } , \Sigma _ { 11 } \otimes \Phi , \psi )$. However, if $X$, $M$ and $\Phi$ are partitioned as

\begin{equation*} X = ( X _ { 1 } , X _ { 2 } ) , M = ( M _ { 1 } , M _ { 2 } ) , \Phi = \left( \begin{array} { c c } { \Phi _ { 11 } } & { \Phi _ { 12 } } \\ { \Phi _ { 21 } } & { \Phi _ { 22 } } \end{array} \right), \end{equation*}

where $X _ { 1 }$ is a $( p \times m )$-matrix, $M _ { 1 }$ is a $( p \times m )$-matrix, and $\Phi _ { 11 }$ is an $( m \times m )$-matrix, $m < n$, then $X _ { 1 } \sim E _ { p , m } ( M _ { 1 } , \Sigma \otimes \Phi _ { 11 } , \psi )$.

Here, if the expectations exist, then $\mathsf{E} ( X ) = M$ and $\operatorname { cov } ( X ) = c \Sigma \otimes \Phi$, where $c = - 2 \psi ^ { \prime } ( 0 )$. An important tool in the study of matrix variate elliptically contoured distributions is the stochastic representation of $X$:

\begin{equation*} X : = M + r A U B ^ { \prime }, \end{equation*}

where $\operatorname{rank} ( \Sigma ) = p _ { 1 }$, $\operatorname{rank} ( \Phi ) = n _ { 1 }$, $U$ is a $( p _ { 1 } \times n _ { 1 } )$-matrix and $\overset{\rightharpoonup} { f n n m e } ( U ^ { \prime } )$ is uniformly distributed on the unit sphere in $\mathbf{R} ^ { p_1 n_1 } $, $r$ is a non-negative random variable, $r$ and $U$ are independent, $\Sigma = A A ^ { \prime }$, and $\Phi = B B ^ { \prime }$. Moreover,

\begin{equation*} \psi ( u ) = \int _ { 0 } ^ { \infty } \Omega _ { p _ { 1 } n _ { 1 } } ( r ^ { 2 } u ) d F ( r ) , u \geq 0, \end{equation*}

where $\Omega _ { p _ { 1 } n _ { 1 } } ( t ^ { \prime } t ^ { \prime } )$, $t \in {\bf R} ^ { p _ { 1 } n _ { 1 } }$ denotes the characteristic function of $\overset{\rightharpoonup} { f n n m e } ( U ^ { \prime } )$, and $F ( r )$ denotes the distribution function of $r$.

References

[a1] K.T. Fang, Y.T. Zhang, "Generalized multivariate analysis" , Springer (1990)
[a2] K.T. Fang, T.W. Anderson, "Statistical inference in elliptically contoured and related distributions" , Allerton Press (1990)
[a3] A.K. Gupta, T. Varga, "Rank of a quadratic form in an elliptically contoured matrix random variable" Statist. Probab. Lett. , 12 (1991) pp. 131–134
[a4] A.K. Gupta, T. Varga, "Elliptically contoured models in statistics" , Kluwer Acad. Publ. (1993)
[a5] A.K. Gupta, T. Varga, "Some applications of the stochastic representation of elliptically contoured distribution" Random Oper. and Stoch. Eqs. , 2 (1994) pp. 1–11
[a6] A.K. Gupta, T. Varga, "A new class of matrix variate elliptically contoured distributions" J. Italian Statist. Soc. , 3 (1994) pp. 255–270
[a7] A.K. Gupta, T. Varga, "Moments and other expected values for matrix variate elliptically contoured distributions" Statistica , 54 (1994) pp. 361–373
[a8] A.K. Gupta, T. Varga, "Normal mixture representation of matrix variate elliptically contoured distributions" Sankhyā Ser. A , 57 (1995) pp. 68–78
[a9] A.K. Gupta, T. Varga, "Some inference problems for matrix variate elliptically contoured distributions" Statistics , 26 (1995) pp. 219–229
[a10] A.K. Gupta, T. Varga, "Characterization of matrix variate elliptically contoured distributions" , Adv. Theory and Practice of Statistics: A Volume in Honor of Samuel Kotz , Wiley (1997) pp. 455–467
How to Cite This Entry:
Matrix variate elliptically contoured distribution. Encyclopedia of Mathematics. URL: http://encyclopediaofmath.org/index.php?title=Matrix_variate_elliptically_contoured_distribution&oldid=14403
This article was adapted from an original article by A.K. Gupta (originator), which appeared in Encyclopedia of Mathematics - ISBN 1402006098. See original article