Improved Aalen–Johansen Estimator Based on Ranked Set Sampling Design

• Activity Number: 346 - Contributed Poster Presentations: Section on Nonparametric Statistics
• Type: Contributed
• Date/Time: Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Section on Nonparametric Statistics
• Author(s): Ying Ma* and Jason Beckstead and Getachew A. Dagne and Hamisu M. Salihu and Ronee Wilson and Alfred Mbah
• Companies: University of South Florida and University of South Florida and University of South Florida and Baylor College of Medicine and University of South Florida and University of South Florida
• Keywords: ranked set sampling; illness death model; Aalen Johansen; Markov process; transition probabilities

Abstract

This study presents a novel methodology to investigate the nonparametric estimation of transition probabilities in illness death model using the ranked set sampling (RSS) design. The RSS sampling design is applied widely in agriculture, environmental science, medicine and survival analysis where the exact measurements of sampling units is costly, but sampling units can be ranked by correlated concomitant variable. RSS is usually a cost-efficient alternate to simple random sampling (SRS) when quantification of all sampling units is expensive. We study the Aalen–Johansen estimator of transition probabilities in illness death Markov model based on RSS design under random censoring time and propose nonparametric estimators of the transition probabilities. We compare the performance of the suggested estimators via simulation study. The results show that the proposed estimator under RSS design outperforms its counterparts in SRS design in several simulation scenarios. Additionally, the proposed methods are applied to a real-world cancer data set for illustration.