Summary
The present paper presents another proof of the known result that the necessary best estimator of order two does not exist for the most general class of linear homogeneous unbiased estimators.
Similar content being viewed by others
References
Hege, V.S.: An optimum property of the Horvitz-Thompson estimate. J. Amer. Statist. Assoc.62, 1967, 1013–1017.
Horwitz, D.G., andD.J. Thompson: A generalization of sampling without replacement from a finite universe. J. Amer. Statist. Assoc.47, 1952, 663–685.
Lanke, J.: On UMV-estimators in survey sampling. Department of Mathematical Statistics, University of Lund and Lund Institute of Technology. Lund 1972.
Ogus, J.: A note on the “necessary best estimator”. J. Amer. Statist. Assoc.64, 1969, 1350–1352.
Patel, H.C.: A Note necessary best estimators in the class of linear unbiased estimators. Sankhyä Series C36, 1974, 195–196.
Prabhu-Ajgaonkar, S.G.: On a class of linear estimators in sampling with varying probabilities without replacement. J. Amer. Statist. Assoc.60, 1965, 637–642.
—: On the non-existence of a best estimator for the entire class of linear estimators. Sankhyā, Series A31, 1969, 455–462.
Rao, J.N.K., andM.P. Singh: On the choice of estimator in survey sampling. The Australian J. Statist.15, 1973, 95–104.
Yogi, A.K., andP.C. Gupta: On the non-existence of second and higher order necessary best estimators. J. Indian Soc. Agric. Statist.27, 1975, 55–66.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Prabhu-Ajgaonkar, S.G. A note on necessary best estimator of order two. Metrika 31, 1–4 (1984). https://doi.org/10.1007/BF01915176
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF01915176