Abstract
Ranked set sampling (RSS) uses fixed set size and number of cycles (or replications). In real life however, we may encounter problems that requiring random set size or number of cycles or both. In dealing with such problems we suggest several unbiased estimators of the population mean using random ranked set sampling (RRSS) method in case of perfect ranking and imperfect ranking. The efficiencies of the estimators of the population mean under RRSS and RSS are compared in the case of perfect ranking. The results show, under certain conditions, the efficiency of estimators is improved by using RRSS in the case of perfect ranking. Finally the asymptotic properties of the proposed estimators of the population mean are discussed for prefect and imperfect ranking.
| Original language | English |
|---|---|
| Pages (from-to) | 311-324 |
| Number of pages | 14 |
| Journal | Journal of Nonparametric Statistics |
| Volume | 15 |
| Issue number | 3 |
| DOIs | |
| State | Published - Jun 2003 |
Keywords
- Asymptotic properties
- Discrete uniform distribution
- Efficiency
- Errors in ranking
- Random number of replications
- Random set size
- Ranked set sampling
- Relative precision
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty