An efficient class of estimators of finite population variance using quartiles

• Published in: Journal of applied statistics 2016-07, Vol.43 (10), p.1945-1958
• Main Authors: Singh, Housila P., Pal, Surya K.
• Format: Article
• Language: English
• Subjects: Applied statistics; Auxiliary variable; bias; Empirical analysis; Estimators; Mathematical analysis; mean squared error; Population; Quartiles; Random sampling; simple random sampling; Studies; study variable; Variance
• ISSN: 0266-4763; 1360-0532
• DOI: 10.1080/02664763.2015.1125865

In this paper, we have proposed a class of estimators of finite population variance using known values of parameters related to an auxiliary variable such as quartiles and its properties are studied in simple random sampling. The suggested class of ratio-type estimators has been compared with the usual unbiased, ratio estimators and the class of ratio-type estimators due to Singh et al. [Improved estimation of finite population variance using quartiles, Istatistik - J. Turkish Stat. Assoc. 6(3) (2013), pp. 166-121] and Solanki et al. [Improved ratio-type estimators of finite population variance using quartiles, Hacettepe J. Math. Stat. 44(3) (2015), pp. 747-754]. An empirical study is also carried out to judge the merits of the proposed estimator over other existing estimators of population variance using natural data set. It is found that the proposed class of ratio-type estimators ' ' is superior to the usual unbiased estimator and the estimators recently proposed by Singh et al. [Improved estimation of finite population variance using quartiles, Istatistik - J. Turkish Stat. Assoc. 6(3) (2013), pp. 166-121] and Solanki et al. [Improved ratio-type estimators of finite population variance using quartiles, Hacettepe J. Math. Stat. 44(3) (2015), pp. 747-754].