Statistical Papers
DOI 10.1007/s00362-007-0079-y
REGULAR ARTICLE
Ratio estimator for the population mean using ranked
set sampling
Cem Kadilar · Yesim Unyazici · Hulya Cingi
Received: 20 February 2006 / Revised: 4 June 2007
© Springer-Verlag 2007
Abstract We adapt the ratio estimation using ranked set sampling, suggested by
Samawi and Muttlak (Biometr J 38:753–764, 1996), to the ratio estimator for the pop-
ulation mean, based on Prasad (Commun Stat Theory Methods 18:379–392, 1989), in
simple random sampling. Theoretically, we show that the proposed ratio estimator for
the population mean is more efficient than the ratio estimator, in Prasad (1989), in all
conditions. In addition, we support this theoretical result with the aid of a numerical
example.
Keywords Ratio estimator · Ranked set sampling · Simple random sampling ·
Efficiency
Mathematics Subject Classification (2000) 62D05
1 Introduction
The traditional ratio estimator for the population mean
_
Y of the study variable y is
defined by
_
y
r
=
_
y
_
x
_
X =
ˆ
R
_
X (1)
in which it is assumed that the population mean
_
X of the auxiliary variable x is
known. Here
_
y is the sample mean of the study variable and
_
x is the sample mean of
the auxiliary variable.
C. Kadilar (B ) · Y. Unyazici · H. Cingi
Department of Statistics, Hacettepe University, Beytepe, 06800 Ankara, Turkey
e-mail: kadilar@hacettepe.edu.tr
123