The Effect of Differential Recruitment, Non-response and Non-recruitment on Estimators for Respondent-Driven Sampling

TL;DR

This paper compares five estimators for respondent-driven sampling through simulations, revealing no single best estimator across all conditions and identifying when each performs best.

Contribution

It provides a comprehensive simulation-based comparison of existing estimators, highlighting their strengths and weaknesses under different sampling conditions.

Findings

No estimator consistently outperforms others across all scenarios.

Different estimators are preferable depending on specific sampling conditions.

The study clarifies the conditions under which each estimator is most effective.

Abstract

Respondent-driven sampling is a widely-used network sampling technique, designed to sample from hard-to-reach populations. Estimation from the resulting samples is an area of active research, with software available to compute at least four estimators of a population proportion. Each estimator is claimed to address deficiencies in previous estimators, however those claims are often unsubstantiated. In this study we provide a simulation-based comparison of five existing estimators, focussing on sampling conditions which a recent estimator is designed to address. We find no estimator consistently out-performs all others, and highlight sampling conditions in which each is to be preferred.