Mean estimate in ranked set sampling using a length-biased concomitant variable

Abstract

In this paper, a ranked set sampling procedure with ranking based on a length-biased concomitant variable is proposed. The estimate for population mean based on this sample is given. It is proved that the estimate based on ranked set samples is asymptotically more efficient than the estimate based on simple random samples. Simulation studies are conducted to present the properties of the proposed estimate for finite sample size. Moreover, the consequence of ignoring length bias is also addressed by simulation studies and the real data analysis.

Keywords:

• concomitant variable
• length-biased
• mean estimate
• ranked set sample

Additional information

Funding

This work is supported by NNSF of China 71201095 and This work is supported by State Key Program of NNSF of China 91546202.