Unbiased estimation of P(X>Y) using ranked set sample data

Author: Sengupta Samindranath  

Publisher: Taylor & Francis Ltd

ISSN: 0233-1888

Source: Statistics, Vol.42, Iss.3, 2008-06, pp. : 223-230

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

The problem considered is that of an unbiased estimation of P[X>Y] using ranked set sample data for two independent random variables X and Y with unknown probability distributions. Postulating a model for imperfect ranking, it is proved that the ranked set samples provide an unbiased estimator with smaller variance as compared with simple random samples of same sizes, even when the rankings are imperfect. It is further shown that the ranked set sampling provides maximum efficiency when the rankings are perfect.