Science in China Series A: Mathematics

, Volume 45, Issue 7, pp 845–858 | Cite as

Existence of the uniformly minimum risk equivariant estimators of parameters in a class of normal linear models

Article
  • 28 Downloads

Abstract

In this paper, we study the existence of the uniformly minimum risk equivariant (UMRE) estimators of parameters in a class of normal linear models, which include the normal variance components model, the growth curve model, the extended growth curve model, and the seemingly unrelated regression equations model, and so on. The necessary and sufficient conditions are given for the existence of UMRE estimators of the estimable linear functions of regression coefficients, the covariance matrixV and (trV)α, where α > 0 is known, in the models under an affine group of transformations for quadratic losses and matrix losses, respectively. Under the (extended) growth curve model and the seemingly unrelated regression equations model, the conclusions given in literature for estimating regression coefficients can be derived by applying the general results in this paper, and the sufficient conditions for non-existence of UMRE estimators ofV and tr(V) are expanded to be necessary and sufficient conditions. In addition, the necessary and sufficient conditions that there exist UMRE estimators of parameters in the variance components model are obtained for the first time.

Keywords

uniformly minimum risk equivariant estimator affine group of transformations quadratic loss matrix loss 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Potthoff, R. F., Roy, S. N., A generalized multivariate analysis of variance model useful especially for growth curve problem, Biometrika, 1964, 51: 313–326.MATHMathSciNetGoogle Scholar
  2. 2.
    Geisser, S., Growth curve analysis, in Handbook of Statistics (ed. Krishnaih, P. R.), Vol. 1, Amsterdam: North-Holland, 1980, 89–115.Google Scholar
  3. 3.
    Von Roson, D., Maximum likelihood estimates in multivariate linear normal models with special references to the growth curve model, Research Report 135, Department of Mathematics and Statistics, University of Stockholm, Stockholm, Sweden, 1984.Google Scholar
  4. 4.
    Verbyla, A. P., Venables, W. N., An extension of the growth curve model, Biometrika, 1988, 75: 129–138.MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Von Roson, D., Maximum likelihood estimators in multivariate linear normal model, J. Multivariate Annals, 1989, 31: 187–200.CrossRefGoogle Scholar
  6. 6.
    Von Roson, D., Uniqueness conditions for maximum likelihood estimators in a multivariate linear model, J. Statist. Plann. Inference, 1993, 36: 269–276.CrossRefMathSciNetGoogle Scholar
  7. 7.
    Zellner, A., An efficient method of estimating seemingly unrelated regression and tests for aggregation bias, J. Amer. Statist. Assoc., 1962, 57: 348–368.MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Srivastava, V. K., Giles, D. E. A., Seemingly Unrelated Regression Equations Models, New York: Marcel Dekker Inc., 1987.MATHGoogle Scholar
  9. 9.
    Rao, C. R., Linear Statistical Inference and Its application, New York: John Wiley & Sons Inc., 1973.Google Scholar
  10. 10.
    Tan, M., Improved estimators for the GMANOVA problem with application to Monte Carlo Simulation, J. Multivariate Annals., 1991, 38: 262.MATHCrossRefGoogle Scholar
  11. 11.
    Wu, Q. G., Necessary and sufficient conditions for the existence of the UMRE estimator in growth curve models, Science in China, Ser. A, 1995, 38: 287–297.MATHGoogle Scholar
  12. 12.
    Wu, Q. G., Jiang Zhenyu, The existence of the uniformly minimum risk equivariant estimator in SURE model, Commun. Statist. Theory Meth., 1997, 26(1): 113–128.MATHCrossRefGoogle Scholar
  13. 13.
    Wu, Q. G., Existence of the uniformly minimum risk unbiased estimator in seemingly unrelated regression system, Acta Mathematics Sinica, New Series, 1995, 11: 23–28.MATHCrossRefGoogle Scholar
  14. 14.
    Wu, Q. G., Zhang Bo, Existence of the UMRE estimator in growth curve models, J. Sys. Sci. Math. Scis. (in Chinese), 1998, 18(2): 182–196.MATHGoogle Scholar
  15. 15.
    Wei, F. R., Several results on parameter estimation in SURE model with special covariance structure, J. Sys. Sci. Math. Scis. (in Chinese), 1999, 19(1): 86–94.MATHGoogle Scholar
  16. 16.
    Wu, Q. G., Some results on parameter estimation in extended growth curve models, Journal of Statistical Planning and Inference, 2000, 88: 285–300.MATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Wu, Q. G., Existence of the UMRU estimators in SURE model with special covariance structures, Chinese Science Bulletin, 1997, 42(14): 1149–1151.MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Science in China Press 2002

Authors and Affiliations

  1. 1.Institute of Systems ScienceAcademy of Mathematics and System Sciences, Chinese Academy of SciencesBeijingChina

Personalised recommendations