|
Abstract:
|
Respondent-driven sampling (RDS) is a network sampling methodology used worldwide to sample key populations at high risk for HIV/AIDS who are not typically reachable by conventional sampling techniques. In RDS, study participants recruit members of their social network to enroll, resulting in an unknown sampling mechanism. Current RDS estimators require many assumptions about the sampling process, including that people recruit uniformly at random from their network. This is likely not true in practice. In this talk, I present a two-sided rational-choice framework to model preferential recruitment. Each person's recruitment and participation choices depend on pairwise utilities, which are functions of observable covariates plus unobserved heterogeneities. I develop inference for this model within a Bayesian framework by approximating the posterior distribution of the covariate preference coefficients via Markov Chain Monte Carlo (MCMC). The algorithm is a form of constrained Metropolis-Hastings. My framework results in a tractable generative model for the RDS sampling mechanism. This greatly enhances both design-based and model-based inference.
|
