Hybrid ranked set sampling scheme

Abstract

Cost-effective sampling methods are of major concern in surveys of natural resources in agriculture, biology, ecology, forestry, fisheries, environmental management, etc. In this paper, we propose a hybrid ranked set sampling (HRSS) scheme for estimation of the population mean. The proposed sampling scheme encompasses several existing ranked set sampling (RSS) schemes, and may help in selecting a smaller number of units to rank. The HRSS scheme provides an unbiased estimator of the population mean, and it is always more precise than the sample mean based on simple random sampling. Extensive Monte Carlo simulations from both symmetric and asymmetric distributions are used to study the performances of the mean estimators based on HRSS and imperfect HRSS schemes. A simulation with real data set is also performed. It is found that HRSS scheme can provide improvements with respect to existing RSS schemes when estimating population mean.

Keywords:

• unbiased estimator
• order statistics
• relative efficiency
• perfect and imperfect rankings
• simple random sampling
• mean squared error

Disclosure statement

No potential conflict of interest was reported by the author(s).