Robust Hybrid Exponential–logarithmic Mean Estimators in the Presence of Outliers under Ranked Set Sampling

Accepted May 2026

Abstract

This study proposes a robust class of hybrid exponential-logarithmic estimators for population mean estimation under ranked set sampling in the presence of outliers and ranking errors. The estimators integrate robust regression methods, including Huber-M, Huber-MM, Hampel-M, Tukey-M, least trimmed squares, and least median of squares to improve resistance to contamination. The bias and mean square error (MSE) expressions of the proposed estimators are derived analytically. Simulation and real-data results show that the proposed estimators outperform existing adapted estimators by achieving lower MSE and greater robustness for both symmetric and asymmetric populations, making them more reliable for practical surveys.