Authors: Raghaw Raman Sinha; Vinod Kumar
Addresses: Department of Mathematics, Dr. B.R. Ambedkar National Institute of Technology, Jalandhar, India ' Department of Mathematics, Dr. B.R. Ambedkar National Institute of Technology, Jalandhar, India
Abstract: The objective of this article is to suggest improved classes of estimators for estimating the population mean using known and unknown variance of study character under incomplete information to improve the efficiency of the usual unbiased estimator suggested by Hansen and Hurwitz (1946). The expressions for bias and mean square error of the proposed classes of estimators are obtained up to the terms of order (n−2) under large sample approximation. Several sub-classes of estimators are introduced and their properties are studied. A comparative study of the suggested classes of estimators is carried out with an empirical study based on real dataset of census handbook published by Government of India.
Keywords: mean estimation; double sampling; non-respondents; bias; mean square error; MSE; known variance; unknown variance; incomplete information; census data; India.
International Journal of Computing Science and Mathematics, 2015 Vol.6 No.5, pp.442 - 458
Received: 20 Dec 2013
Accepted: 20 Aug 2014
Published online: 10 Nov 2015 *