Population Size Estimation Using Multiple Respondent-Driven Sampling Surveys

Brian J Kim; Mark S Handcock

doi:10.1093/jssam/smz055

Population Size Estimation Using Multiple Respondent-Driven Sampling Surveys

J Surv Stat Methodol. 2019 Dec 7;9(1):94-120. doi: 10.1093/jssam/smz055. eCollection 2021 Feb.

Authors

Brian J Kim¹, Mark S Handcock²

Affiliations

¹ Lecturer in the Joint Program in Survey Methodology, University of Maryland, 1218 LeFrak Hall, 7251 Preinkert Dr., College Park, MD 20742, USA.
² Professor at the University of California, 8125 Math Sciences Bldg., Box 951554, Los Angeles, CA 90095, USA.

Abstract

Respondent-driven sampling (RDS) is commonly used to study hard-to-reach populations since traditional methods are unable to efficiently survey members due to the typically highly stigmatized nature of the population. The number of people in these populations is of primary global health and demographic interest and is usually hard to estimate. However, due to the nature of RDS, current methods of population size estimation are insufficient. We introduce a new method of estimating population size that uses concepts from capture-recapture methods while modeling RDS as a successive sampling process. We assess its statistical validity using information from the CDC's National HIV Behavioral Surveillance system in 2009 and 2012.

Keywords: Capture-recapture; Hard-to-reach population sampling; Model-based survey sampling; Network sampling; Without replacement sampling.

© The Author(s) 2019. Published by Oxford University Press on behalf of the American Association for Public Opinion Research. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Abstract

Grants and funding