The Effects of Ranking Error Models on Mean Estimators Based on Ranked Set Sampling


Akdeniz S., YILDIZ T.

Revstat Statistical Journal, vol.21, no.3, pp.347-366, 2023 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 21 Issue: 3
  • Publication Date: 2023
  • Doi Number: 10.57805/revstat.v21i3.406
  • Journal Name: Revstat Statistical Journal
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, zbMATH, Directory of Open Access Journals
  • Page Numbers: pp.347-366
  • Keywords: abalone dataset, mean estimator, Ranked set sampling, ranking error models, relative efficiency
  • Dokuz Eylül University Affiliated: Yes

Abstract

Ranked Set Sampling (RSS) is a sampling method commonly used in recent years. This sampling method is especially useful for studies in medicine, agriculture, forestry and ecology. In this study, the widely used ranking error models in RSS literature are investigated. This study is aimed to explore the effects of ranking error models on the mean estimators based on RSS and some of its modified methods such as Extreme RSS (ERSS) and Percentile RSS (PRSS) for different distribution, set and cycle size in infinite population. Monte Carlo simulation study is conducted for this purpose. Additionally, the study is supported by real life data. It is observed that, RSS and some of its modified methods shows better results than Simple Random Sampling (SRS).