Ranked Set Sampling and its Applications in Survey Sampling (original) (raw)

In this study, we suggest different classes of Hartley-Ross type unbiased estimators for estimating the population mean (Ȳ ) of the study variable Y under ranked set sampling (RSS) and stratified ranked set sampling (StRSS) schemes, using known auxiliary information such as the population coefficient of variation (Cx), coefficient of kurtosis (β2x), coefficient of correlation (ρ), inter-quartile range (Qr), semi-quartile range (Qd) and semi-quartile average (Qa). Estimators are compared in terms of variances, percentage relative root mean squared error PRRMSE and percentage relative bias PRB. The variances of the proposed estimators are obtained up to first order of approximations. It is shown both theoretically and numerically, that proposed Hartley-Ross type unbiased estimators are more efficient than the usual mean estimator under RSS and StRSS schemes. Different ratio-type estimators using stratified double ranked set sampling (StDRSS) and stratified median ranked set sampling (...