, Volume 39, Issue 1, pp 75–84 | Cite as

Locally minimax test of independence in elliptically symmetrical distributions with additional observations

  • N. Giri
  • M. Behara
  • P. Banerjee
I. Publications


LetX=(X ij )=(X 1, ...,X n )’,X i =(X i1, ...,X ip )’,i=1,2, ...,n be a matrix having a multivariate elliptical distribution depending on a convex functionq with parameters, 0,σ. Let ϱ2 2 -2 be the squared multiple correlation coefficient between the first and the remainingp 2+p 3=p−1 components of eachX i . We have considered here the problem of testingH 02=0 against the alternativesH 1 1 -2 =0, ϱ 2 -2 >0 on the basis ofX andn 1 additional observationsY 1 (n 1×1) on the first component,n 2 observationsY 2(n 2×p 2) on the followingp 2 components andn 3 additional observationsY 3(n 3×p 3) on the lastp 3 components and we have derived here the locally minimax test ofH 0 againstH 1 when ϱ 2 -2 →0 for a givenq. This test, in general, depends on the choice ofq of the familyQ of elliptically symmetrical distributions and it is not optimality robust forQ.

Key words

Elliptically symmetric distributions invariance locally best invariant test locally minimax test optimality robust. 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Chu Kai Chung (1973) Estimation and Decision for Linear System with Elliptical Linear Processes; IEEE, Transaction on Automatic Control, pp 499–505Google Scholar
  2. Eaton ML, Kariya T (1983) Multivariate Test with Incomplete Data. Ann Statist, pp 653–665Google Scholar
  3. Giri N (1979) Locally Minimax Test for Multiple Correlations. Canadian J Statist, pp 53–60Google Scholar
  4. Giri N (1988) Locally Minimax Tests in Symmetrical Distributions. Ann Inst Stat Math 40:381–394zbMATHCrossRefMathSciNetGoogle Scholar
  5. Giri N, Das K (to be published) Locally Minimax Tests of Independence with Additional ObservationsGoogle Scholar
  6. Giri N, Kiefer J (1964) Local and Asymptotic Minimax Properties of Multivariate Tests. Ann Math Statist 25:21–35MathSciNetGoogle Scholar
  7. Hartley HO, Hocking RR (1977) The Analysis of Incomplete Data. Biometrics, pp 783–823Google Scholar
  8. Kariya T, Krishnaiah PR, Rao CR (1983) Statistical Inference from Multivariate Normal Population when Some Data is Missing. Development in Statistica, pp 137–148Google Scholar
  9. Kariya T, Sinha B (1985) Nonnull and Optimality Robustness of Some Tests. Ann Statist 13:1182–1197zbMATHMathSciNetGoogle Scholar
  10. McGraw DK, Wagner JF (1968) Elliptically Asymmetric Distributions. IEEE Trans Inform Theory, pp 110–120Google Scholar
  11. Perron F (1987) Test sur l’indépendance avec information additionnelle. Rapport de recherche. Département de Mathématiques et de Statistique, Université de MontréalGoogle Scholar
  12. Sutradhar BC, Ali MM (1986) Estimation of the Parameters of a Regression Model with a MultivariatT Error Variable. Commun Statist Theor Meth 15:429–450zbMATHMathSciNetGoogle Scholar
  13. Zellner A (1976) Bayesian and Non-Bayesian Analysis of the Regression Model with Multivariate Student-t Error Term. JASA 71:400–405zbMATHMathSciNetGoogle Scholar
  14. Wijsman RA (1967) Cross Section of Orbits and Their Applications to Densities of Maximal Invariants. Fifth Barkeley Symp, Vol 1. pp 389–400MathSciNetGoogle Scholar

Copyright information

© Physica-Verlag GmbH 1992

Authors and Affiliations

  • N. Giri
    • 1
  • M. Behara
    • 2
  • P. Banerjee
    • 3
  1. 1.Dépt. de Math. et Stat.Université de MontréalMontrealCanada
  2. 2.Dept. of Math.McMaster UniversityHamiltonCanada
  3. 3.Dept. of Math. & Stat.Univ. of New-BurnswickFredrictonCanada

Personalised recommendations