Polish Statistical Association
Central Statistical Office of Poland
Subject: Economics, Statistics & Probability
ISSN: 1234-7655
eISSN: 2450-0291
SEARCH WITHIN CONTENT
Keywords : bias, linear regression estimator, mean squared error, natural population, simple random sampling.
Citation Information : Statistics in Transition New Series. Volume 17, Issue 4, Pages 591-604, DOI: https://doi.org/10.21307/stattrans-2016-042
License : (CC BY 4.0)
Published Online: 06-July-2017
The present paper deals with a new median based ratio estimator for the estimation of finite population means in the absence of an auxiliary variable. The bias and mean squared error of the proposed median based ratio estimator are obtained. The performance of the median based ratio estimator is compared with that of the SRSWOR sample mean, ratio estimator and linear regression estimator for certain natural population. It is shown from the numerical comparisons that the proposed median based ratio estimator outperforms the SRSWOR sample mean, ratio estimator and also the linear regression estimator.