Kybernetika 52 no. 5, 724-734, 2016

On admissibility of linear estimators in models with finitely generated parameter space

Ewa Synówka-Bejenka and Stefan ZontekDOI: 10.14736/kyb-2016-5-0724


The paper refers to the research on the characterization of admissible estimators initiated by Cohen \cite{Cohen}. In our paper it is proved that for linear models with finitely generated parameter space the limit of a sequence of the unique locally best linear estimators is admissible. This result is used to give a characterization of admissible linear estimators of fixed and random effects in a random linear model for spatially located sensors measuring intensity of a source of signals in discrete instants of time.


admissibility, linear model, linear estimation, linear prediction, admissibility among an affine set, locally best estimator


62F10, 62J10


  1. J. K. Baksalary and A. Markiewicz: Admissible linear estimators in the general Gauss-Markov model. J. Statist. Plann. Inference 19 (1988), 349-359.   DOI:10.1016/0378-3758(88)90042-0
  2. A. Cohen: All admissible estimates of the mean vector. Ann. Math. Statist. 37 (1966), 458-463.   DOI:10.1214/aoms/1177699528
  3. S. Gnot and J. Kleffe: Quadratic estimation in mixed linear models with two variance components. J. Statist. Plann. Inference 8 (1983), 267-279.   DOI:10.1016/0378-3758(83)90045-9
  4. S. Gnot, E. Rafajłowicz and A. Urbańska-Motyka: Statistical inference in linear model for spatially located sensors and random inputs. Ann. Inst. Statist Math. 53 (2001), 370-379.   DOI:10.1023/a:1012426923971
  5. A. S. Goldberger: Best linear unbiased prediction in the generalized linear regression model. J. Amer. Statist. Assoc. 57 (1962), 369-375.   DOI:10.1080/01621459.1962.10480665
  6. J. Gro{\ss} and A. Markiewicz: Characterization of admissible linear estimators in the linear model. Linear Algebra Appl. 388 (2004), 239-248.   DOI:10.1016/s0024-3795(03)00459-2
  7. D. A. Harville: Extension of the Gauss-Markov theorem to include the estimation of random effects. Ann. Statist. 2 (1976), 384-395.   DOI:10.1214/aos/1176343414
  8. C. R. Henderson: Estimation of genetic parameters (abstract). Ann. Math. Statist. 21 (1950), 309-310.   CrossRef
  9. C. R. Henderson: Selection index and expected genetic advance. In: Statistical Genetics and Plant Breeding (W. D. Hanson and H. F. Robinson, eds.), NAS-NRC 982, Washington 1963, pp. 141-163.   CrossRef
  10. J. Jiang: A derivation of BLUP-Best linear unbiased predictor. Statist. Probab. Lett. 32 (1997), 321-324.   DOI:10.1016/s0167-7152(96)00089-2
  11. W. Klonecki and S. Zontek: On the structure of admissible linear estimators. J. Multivariate Anal. 24 (1988), 11-30.   DOI:10.1016/0047-259x(88)90098-x
  12. L. R. LaMotte: Admissibility in linear estimation. Ann. Statist. 10 (1982), 245-255.   DOI:10.1214/aos/1176345707
  13. L. R. LaMotte: On limits of uniquely best linear estimators. Metrika 45 (1997), 197-211.   DOI:10.1007/bf02717103
  14. X. Q. Liu, J. Y. Rong and X. Y. Liu: Best linear unbiased prediction for linear combinations in general mixed linear models. J. Multivariate Anal. 99 (2008), 1503-1517.   DOI:10.1016/j.jmva.2008.01.004
  15. A. Olsen, J. Seely and D. Birkes: Invariant quadratic unbiased estimation for two variance components. Ann. Statist. 4 (1976), 878-890.   DOI:10.1214/aos/1176343586
  16. C. R. Rao: Estimation of parameters in a linear model. Ann. Statist. 4 (1976), 1023-1037.   DOI:10.1214/aos/1176343639
  17. C. R. Rao: Estimation in linear models with mixed effects: a unified theory. In: Proc. Second International Tampere Conference in Statistics (T. Pukkila and S. Puntanen, eds.), Dept. of Mathematical Sciences, Univ. of Tampere, Tampere 1987, pp. 73-98.   CrossRef
  18. G. K. Robinson: That BLUP is a good thing-the estimation of random effects. Statist. Sci. 6 (1991), 15-51.   DOI:10.1214/ss/1177011933
  19. W. Shiqing, M. Ying and F. Zhijun: Integral expression form of admissible linear estimators of effects in linear mixed models. In: Proc. 2010 International Conference on Computing, Control and Industrial Engineering, IEEE, Wuhan 2010, pp. 56-60.   DOI:10.1109/ccie.2010.133
  20. C. Stępniak: On admissible estimators in a linear model. Biometrical J. 26 (1984), 815-816.   DOI:10.1002/bimj.4710260725
  21. C. Stępniak: A complete class for linear estimation in a general linear model. Ann. Inst. Statist. Math. A 39 (1987), 563-573.   DOI:10.1007/bf02491490
  22. C. Stępniak: Admissible invariant esimators in a linear model. Kybernetika 50 (2014), 310-321.   DOI:10.14736/kyb-2014-3-0310
  23. E. Synówka-Bejenka and S. Zontek: A characterization of admissible linear estimators of fixed and random effects in linear models. Metrika 68 (2008), 157-172.   DOI:10.1007/s00184-007-0149-0
  24. Y. Tian: A new derivation of BLUPs under random-effects model. Metrika 78 (2015), 905-918.   DOI:10.1007/s00184-015-0533-0
  25. S. Zontek: On characterization of linear admissible estimators: an extension of a result due to C. R. Rao. J. Multivariate Anal. 23 (1987), 1-12.   DOI:10.1016/0047-259x(87)90174-6
  26. S. Zontek: Admissibility of limits of the unique locally best linear estimators with application to variance components models. Probab. Math. Statist. 9 (1988), 29-44.   CrossRef