2017/12/25 by Miles Q. Ott, Ott, Miles Q., Krista J. Gile +7
Mathematics · Medicine · #Applications (stat.AP) #Census and Population Estimation #FOS: Computer and information sciences #HIV, Drug Use, Sexual Risk #HIV/AIDS Research and Interventions
paper · pdf · doi:10.48550/arxiv.1712.09149
openalex publication_date 2017/12/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
People who inject drugs are an important population to study in order to\nreduce transmission of blood-borne illnesses including HIV and Hepatitis. In\nthis paper we estimate the HIV and Hepatitis C prevalence among people who\ninject drugs, as well as the proportion of people who inject drugs who are\nfemale in Mauritius. Respondent driven sampling (RDS), a widely adopted\nlink-tracing sampling design used to collect samples from hard-to-reach human\npopulations, was used to collect this sample. The random walk approximation\nunderlying many common RDS estimators assumes that each social relation (edge)\nin the underlying social network has an equal probability of being traced in\nthe collection of the sample. This assumption does not hold in practice. We\nshow that certain RDS estimators are sensitive to the violation of this\nassumption. In order to address this limitation in current methodology, and the\nimpact it may have on prevalence estimates, we present a new method for\nimproving RDS prevalence estimators using estimated edge inclusion\nprobabilities, and apply this to data from Mauritius.\n