A Class of Super-Efficient Estimators of the Normal Variance: A Study on Sample Size Preference

K. Sivasakthi¹ , Martin L. William²

Section:Research Paper, Product Type: Isroset-Journal
Vol.5 , Issue.6 , pp.212-221, Dec-2018

CrossRef-DOI:   https://doi.org/10.26438/ijsrmss/v5i6.212221

Online published on Dec 31, 2018

Copyright © K. Sivasakthi, Martin L. William . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

204 Views    199 Downloads    170 Downloads

Abstract :
A class of super-efficient estimators of the variance of a normal population with known mean has been recently constructed by Sivasakthi, Durairajan, and William (2017) through the ‘Delta Method’. The preference for a super-efficient estimator over the asymptotically efficient estimator (say, maximum likelihood estimator) is for ‘large samples’. In this paper, we address the super-efficient estimation of the normal variance when the population mean is known. The issue that is taken up in this paper is on the sample size required for a super-efficient estimator to be preferred over the maximum likelihood estimator and is addressed through a numerical study. The answer is sought for a subset of the class of super-efficient estimators of the normal variance. Mathematics Subject Classification: 62F10, 62F12

Key-Words / Index Term :
Maximum Likelihood Estimators, Super-efficiency

References :
[1] Bahadur, R. R. (1983). Hodges Super-Efficiency. In: Encyclopedia of Statistical Sciences. 3, John-Wiley, 645-646
[2] Basu, D. (1952). Unpublished Thesis
[3] Durairajan, T.M. (2012).Sub-score and Super- Efficient Estimator. In: Navin Chandra and Gopal, G., eds. Applications of Reliability Theory and Survival Analysis, Bonfring, 120-129
[4] Hodges, J. L. (1951). Unpublished
[5] Le Cam, L. (1953). On some asymptotic properties of maximum likelihood estimates and related Baye’s estimates. University of California Publications in Statistics. 1, 277-330.
[6] Le Cam, L. (1956). On the asymptotic theory of estimation and testing hypotheses. In: Neyman, J. ed. Proceedings of the Third Berkeley Symposium on Mathematics and Probability. 1, University of California Press, Berkeley, 129-156
[7] Le Cam, L. (1960). Locally asymptotically normal families of distributions. University of California Publications in Statistics. 3, 37-98
[8] Le Cam, L. (1972). Limits of experiments. In: Proceedings of the Sixth Berkeley Symposium on Mathematics and Probability. 1, University of California Press, Berkeley, 245-261
[9] Sethuraman, J. (2004). Are Super- Efficient Estimators Super-powerful?. Communications in Statistics-Theory and Methods. 33(9), 2003-2013
[10] Sivasakthi, K., Durairajan, T. M., and William, M. L. (2017), Obtaining Super-Efficient Estimators for a Real-Valued Parameter: Delta Method. International Journal of Applied Mathematics and Statistical Sciences, 6(1), 81-88.
[11] Sivasakthi, K., Sakthivel, R. and William, M. L. (2017). Preference for a class of Super-Efficient Estimators of the normal mean: A study on sample size requirement. International Journal of Statistics and Applied Mathematics, 2(6), 241-249
[12] Stein, C. (1956). Inadmissibility of the usual estimator for the mean of a normal distribution. In: Neyman, J. ed. Proceedings of the Third Berkeley Symposium on Mathematics and Probability. 1, University of California Press, Berkeley, 197-206