Multivariate Normal Distribution and Related Inference: VI
Dr. Sumitra Purkayastha, Professor
Applied Statistics Unit, Indian Statistical Institute, Kolkata sumitra@isical.ac.in
1 Inference about a multivariate normal dispersion matrix
Objectives of the lecture We consider independent and identically distributed observationsX1, . . . ,Xn
having a common Np(µ,Σ)distribution, whereµis anunknownp×1vector. Our goals:
• To develop likelihood ratio test for
H0 :Σ=σ2Ip against H1:H0 is f alse.
(a) Expression for maximum likelihood estimator of(µ, σ)under H0and also without any restric- tion
(b) Expression for the likelihood ratio test statisticΛ (c) Asymptotic distribution of−2 log Λunder H0
• To develop likelihood ratio test for independence of two disjoint partitions ofX1.
(a) Expressions for maximum likelihood estimator of(µ, σ)under H0and also without any restric- tion
(b) Expression for the likelihood ratio test statisticΛ
(c) Exact null distribution of−2 log Λunder H0, leading to a distribution theoretic question, and asymptotic null distribution as well
1.1 Test for sphericity
Distributional assumption and formulation of the problem
We assume thatX1, . . . ,Xnare independent and identically distributed observations having a com- mon Np(µ,Σ)distribution, whereµis anunknownp×1vector.
We wish to test the following hypothesis:
H0 :Σ=σ2Ip against H1:H0 is f alse.
WhenΣ=σ2Ip, the common density function ofXi’s is given by C·exp(−(x−µ)T(x−µ)/2).
Thus the (common) density function is constant on spheres. This is why the problem of testing H0:Σ=σ2Ipis known in the multivariate analysis literature astest for sphericity.
Descriptive statistics Under assumption of normality, the following descriptive statistics are suffi- cient.
Sample mean= ¯X = 1 n
n
X
i=1
Xi
Sample dispersion matrix=S= 1 n
n
X
i=1
(Xi−X)(X¯ i−X¯)T.
We assume thatn≥p+ 1. This will ensurealmost sureinvertibility ofS.
We shall mention the likelihood ratio test statistic and state also its asymptotic distribution.
Expressions for maximum likelihood estimators Maximum likelihood estimator of(µ, σ2)under H0:
( ˆµ,σˆ2) = ( ¯X, p−1tr(S)) Maximum likelihood estimator of(µ,Σ)without any restriction:
( ˆµ,Σ) = ( ¯ˆ X,S).
Expression for the likelihood ratio test statisticΛand its asymptotic distribution The expression for the log likelihood ratio statistic is given by
−2 log Λ =np(loga0−logg0) =nplog(a0/g0), where
a0 :=arithmetic mean of the eigenvalues of S=trace(S)/p, and
g0 :=geometric mean of the eigenvalues of S= (det(S))1/p. We reject H0ifa0/g0is too large.
The asymptotic distribution of−2 log Λunder H0 isχ2f, wheref := (p−1)(p+ 2)/2.
1.2 Test for independence
Distributional assumption and formulation of the problem
We assume thatX1, . . . ,Xnare independent and identically distributed observations having a com- mon Np(µ,Σ)distribution, whereµis anunknownp×1vector.
Suppose we partition eachXias follows:
Xi =
Xi,1
Xi,2
.
The (random) vectorXi,1(Xi,2) is of sizep1×1(p2×1), wherep1+p2=p.
The corresponding partitions inµandΣare µ=
µ1 µ2
, Σ=
Σ11 Σ12 Σ21 Σ22
.
The mean vector ofXi,1(Xi,2) isµ1(µ2). The dispersion matrix ofXi,1(Xi,2) isΣ11(Σ22). The covariance matrix ofXi,1 andXi,2isΣ12.
Distributional assumption and formulation of the problem
We wish to test if X1,1 andX1,2 are independent. In terms of the partition ofΣit can be stated equivalently as
H0 :Σ=0.
Descriptive statistics Under assumption of normality, the following descriptive statistics are suffi- cient.
Sample mean= ¯X = 1 n
n
X
i=1
Xi
Sample dispersion matrix=S= 1 n
n
X
i=1
(Xi−X)(X¯ i−X¯)T.
We consider the partitions ofX¯ andS, analogous to those consider earlier as follows:
X¯ = X¯1
X¯2
, S=
S11 S12
S21 S22
.
We assume thatn≥p+ 1. This will ensurealmost sureinvertibility ofS.and hence of each ofS11 andS22.
We shall mention the likelihood ratio test statistic and state also its asymptotic distribution.
Expressions for maximum likelihood estimators Maximum likelihood estimator of(µ,Σ)under H0:
( ¯X,
S11 S12 S21 S22
)
Maximum likelihood estimator of(µ,Σ)without any restriction:
( ˆµ,Σ) = ( ¯ˆ X,S).
Expression for the likelihood ratio test statisticΛand its null distribution Likelihood ratio test statistic is given by
−2 log Λ =−nlog
|S22−S21S−111S12|
|S22|
=−nlog |Ip−S−122S21S−111S12| .
The exact null distribution ofΛ2/nisΛ(p2, n−1−p1, p1),Wilks’ lambda distribution with parameters p2, n−1−p1, p1.
Question:What is Wilks’ lambda (Λ(p, m, n)) distribution?
The asymptotic null distribution of−2 log Λisχ2p1p2. 1.3
Contents of the lectureWe considered independent and identically distributed observationsX1, . . . ,Xn
having a common Np(µ,Σ)distribution, whereµis anunknownp×1vector. Our goals have been the following:
• To develop likelihood ratio test for
H0 :Σ=σ2Ip against H1:H0 is f alse.
(a) Maximum likelihood estimator ofµunder H0and also without any restriction (b) Expression for the log-likelihood ratio test statistic−2Λ
(c) Asymptotic distribution of−2 log Λunder H0
• To develop likelihood ratio test for independence of two disjoint partitions ofX1.
(a) Expressions for maximum likelihood estimator of(µ, σ)under H0and also without any restriction
(b) Expression for the likelihood ratio test statisticΛ
(c) Exact null distribution of−2 log Λunder H0, leading to a distribution theoretic question, and asymptotic null distribution as well