Correcting for Preferential Recruitment in Respondent-Driven Sampling

• Activity Number: 361
• Type: Contributed
• Date/Time: Tuesday, August 11, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Isabelle Beaudry* and Krista J. Gile and Corinne M. Mar
• Companies: University of Massachusetts Amherst and University of Massachusetts Amherst and University of Washington
• Keywords: Respondent-Driven Sampling ; Preferential Recruitment ; Model-Assisted ; Network Inference ; Social Networks ; Hard-to-Reach Human Populations

Abstract

Respondent-driven sampling (RDS) is a sampling mechanism that has proven very effective to sample hard-to-reach human populations connected through social networks. A small number of individuals typically known to the researcher are initially sampled and asked to recruit a small fixed number of their contacts who are also members of the target population. Each subsequent sampling waves are produced by peer recruitment until a desired sample size is achieved. However, the researcher's lack of control over the sampling process has posed a number of challenges to producing valid statistical inference from RDS data. For instance, it is often assumed that participants recruit completely at random among their contacts. However, it has been observed in practice that participants sometimes systematically recruit with a higher probability individuals with a specific characteristic. Existing literature suggests that RDS prevalence estimators are greatly sensitive to this assumption. The main contribution of this study is to propose a Model-Assisted approach to correct current RDS estimators for the bias introduced by preferential recruitment.