Estimating Hidden Population Sizes with Venue-based Sampling

Abstract

Background: Researchers use a variety of population size estimation methods to determine the sizes of key populations at elevated risk of human immunodeficiency virus (HIV)/acquired immune deficiency syndrome (AIDS), an important step in quantifying epidemic impact, advocating for high-risk groups, and planning, implementing, and monitoring prevention, care, and treatment programs. Conventional procedures often use information about sample respondents’ social network contacts to estimate the sizes of key populations of interest. Recent work proposes a generalized network scale-up method that combines two samples – a traditional sample of the general population and a link-tracing sample of the hidden population – and produces more accurate results with fewer assumptions than conventional approaches. Methods: We extended the generalized network scale-up method from link tracing samples to samples collected with venue-based sampling designs popular in sampling key populations at risk of HIV. Our method obviates the need for a traditional sample of the general population, as long as the size of the venue-attending population is approximately known. We tested the venue-based generalized network scale-up method in a comprehensive simulation evaluation framework. Results: The venue-based generalized network scale-up method provided accurate and efficient estimates of key population sizes, even when few members of the key population were sampled, yielding average biases below ±6% except when false-positive reporting error is high. It relies on limited assumptions and, in our tests, was robust to numerous threats to inference. Conclusions: Key population size estimation is vital to the successful implementation of efforts to combat HIV/AIDS. Venue-based network scale-up approaches offer another tool that researchers and policymakers can apply to these problems.

Understanding Neighborhoods’ Impact on Youth Substance Use and Mental Health Outcomes in Paterson, New Jersey: Protocol for a Community-Based Participatory Research Study

“…This study proposes innovative methods such as venue-based sampling to recruit and engage with a hard-to-reach population in Paterson, New Jersey. Few studies have used venue-based sampling in youth studies; however, those that have, offered beneficial results through recruitment of hard-to-reach youth [ 52 , 73 ]. A majority of youths are recruited from schools; however, this can lead to bias and neglect of youth who are truant or not connected to youth-serving organizations.…”

“…The study will use a convergent [ 50 ], mixed methods design involving multiple data collection components and the analysis of a ministrative data source, designed with the strengths of complex interventions framework in mind. Venue-based sampling [ 51 , 52 ], purposive sampling [ 53 , 54 ], and snowball sampling [ 55 ] will be the 2 primary sources of recruitment for participants. The youth and community advisory board will be used as key informants to identify places where youth often congregate when they are not in school.…”

“…Venue-based sampling [ 51 , 52 ] is a recruitment strategy that entails targeted recruitment through preidentified venues in Paterson, New Jersey, where youth congregate. This sampling method will occur in 1 of 2 ways.…”

A Sample Size Formula for Network Scale-up Studies

“…Feehan and Salganik (2016) introduce a method that generalizes NSUM (called G-NSUM) by recognizing that in an undirected network, total in-degrees and out-degrees must be equal, a fact that can be exploited when two samples are obtainable. The G-NSUM was further generalized for venue-based sampling (Verdery et al 2019). While these methods offer improved and more efficient estimates, the classic NSUM method remains widely used due to its simplicity.…”

Using Social Networks to Estimate the Number of COVID-19 Cases: The Incident (Hidden COVID-19 Cases Network Estimation) Study Protocol

“…The network scale-up method (NSUM), which was first proposed by Bernard et al [ 16 , 17 ], is among the recommended methods to estimate the hidden population available in the literature. NSUM has been widely used to estimate the size of hard-to-reach populations due to the stigmatizing nature of its knowledge, such as HIV [ 18 ], injuries [ 19 ], men who have sex with men (MSM) [ 20 ], and others. It relies on the idea that the probability of knowing someone in a specific subpopulation is related to the relative size of that subpopulation, i.e., the proportion computed based on the population size of all individuals.…”