Analysis of Ordinal Populations from Judgment Post-Stratification

TL;DR

This paper develops new estimation methods for ordinal populations using judgment post-stratification (JPS) sampling, addressing issues like empty strata and multiple ranking resources, with applications to medical data.

Contribution

It introduces novel estimators for ordinal populations from JPS samples, including methods for empty strata and multiple ranking sources, validated through extensive simulations and real data.

Findings

New estimators outperform existing methods in simulations

Effective handling of empty strata in JPS sampling

Successful application to bone mineral data for women 50+

Abstract

In surveys requiring cost efficiency, such as medical research, measuring the variable of interest (e.g., disease status) is expensive and/or time-consuming; However, we often have access to easily attainable characteristics about sampling units. These characteristics are not typically employed in the data collection process. Judgment post-stratification (JPS) sampling enables us to supplement the random samples from the population of interest with these characteristics as ranking information. In this paper, we develop methods based on JPS samples for the estimation of categorical ordinal populations. We develop various estimators from JPS data even for a situation where JPS suffers from empty strata. We also propose JPS estimators using multiple ranking resources. Through extensive numerical studies, we evaluate the performance of the methods in the estimation of the population. Finally, the developed estimation methods are applied to bone mineral data to estimate the bone disorder status of women aged 50 and older.