Design-based estimators of distribution function in ranked set sampling with an application

TL;DR

This paper develops new empirical distribution function estimators within ranked set sampling for finite populations, demonstrating their asymptotic properties and superior efficiency, especially with level-2 sampling design, through simulations and real data application.

Contribution

It introduces novel EDF estimators for finite populations in RSS, analyzes their asymptotic behavior, and compares their efficiency across different sampling levels.

Findings

Level-2 sampling yields more efficient EDF estimators.

Imperfect ranking impacts estimator performance.

Real data application confirms theoretical advantages.

Abstract

Empirical distribution functions (EDFs) based on ranked set sampling (RSS) and its modifications have been examined by many authors. In these studies, the proposed estimators have been investigated for infinite population setting. However, developing EDF estimators in finite population setting would be more valuable for areas such as environmental, ecological, agricultural, biological, etc. This paper introduces new EDF estimators based on level-0, level-1 and level-2 sampling designs in RSS. Asymptotic properties of the new EDF estimators have been established. Numerical results have been obtained for the case when ranking is imperfect under different distribution functions. It has been observed that level-2 sampling design provides more efficient EDF estimator than its counterparts of level-0, level-1 and simple random sampling. In real data application, we consider a pointwise estimate of distribution function and estimation of the median of sheep's weights at seven months using RSS based on level-2 sampling design.