On regression estimators for different stratified sampling schemes. Issue 6 (2nd November 2017)

• Record Type: Journal Article
• Authors: Chatterjee, Arpita; Samawi, Hani; Yu, Lili; Linder, Daniel; Cai, Jingxian; Vogel, Robert
• Is Part Of: Journal of statistics & management systems. Volume 20:Issue 6(2017)
• Page Start: 1147
• Page End: 1165
• Publication Date: 2017-11-02
• Subjects: Ranked set sampling -- Stratified ranked set sampling -- Regression estimator; Statistics -- Periodicals; Mathematical models -- Periodicals; Mathematical models; Statistics; Periodicals; 519.5
• DOI: 10.1080/09720510.2017.1411027
• Languages: English
• ISSNs: 0972-0510

Abstract

Abstract: Two types of stratified regression estimators for the population mean, the separate and the combined estimators, are investigated using stratified random sampling scheme (SSRS) and stratified ranked set sampling (SRSS). We derived mean and variance of the proposed estimators. In addition, we compared the performance of the regression estimators using SRSS with respect to SSRS by simulation. Our derivations and simulations revealed that our proposed estimators are unbiased and using SRSS is more efficient than using SSRS. The procedure are illustrated by using the bilirubin levels in babies in a neonatal intensive care unit data.