***** To join INSNA, visit *****

Call for Abstracts, “Multidisciplinary Perspectives on RDS Inference” Track

for Sunbelt XXXIV in St Pete Beach, FL, February 18 – 23, 2014

Respondent Driven Sampling (RDS) is an effective social network based recruitment tool to reach hidden populations at high risk of HIV and other blood borne diseases. RDS is also a sampling method to which statistical models have been widely applied in an effort to generate population inferences. These models contain certain assumptions that may in practice be difficult to meet.  For instance, most RDS inference models rely on participants’ accurate reporting of social network size and composition, and are based on underlying assumptions about participants’ social network structure, peer recruitment behavior, and recruitment processes. The validity of RDS inference is subject to question if any of these assumptions are violated in the sample recruitment process. At the moment there is a disjunction whereby epidemiologists and HIV researchers use statistical methods on RDS data unaware that they rely on strong assumptions while statisticians rely on unrealistic assumptions to justify the methods they develop. The better use of RDS data to produce better point estimates and appropriate measure of certainty call scholars with various expertise to share their knowledge.

Drs. JiangHong Li, Thomas Valente,  Robert Heimer, Mark Handcock are organizing a special theme track on “Multidisciplinary Perspectives on RDS Inference” for Sunbelt XXXIV in St Pete Beach, FL, February 18 – 23, 2014 ( We encourage social network researchers, HIV researchers, social behavioral researchers and statisticians who are interested in the one or more of the following areas to submit abstract and join our special theme track:

-          Implementation challenges and promises in meeting RDS assumptions in the field;

-          Explorations of real RDS datasets to determine if the assumptions are being met and, if not, the extent to which the violations compromise or prevent inference. 

-          Qualitative and quantitative empirical findings regarding RDS network reporting behavior, peer recruitment behavior patterns and recruitment dynamics;

-          Statistical or simulation assessment of RDS model sensitivity to model assumption violation;

-          Assessment of RDS performance by comparing with other data sources or simulation with empirical network data;

-          Development of improved RDS inference models with more realistic assumptions.

-          Development of alternative statistical models to make population estimates using RDS data.

-          Development of statistical diagnostics tools to indicate violation of assumptions.

-          Related research findings that have implication to RDS development, or contribute to understanding of social network information reporting behaviors, peer recruitment behavior and dynamics.

Interested individuals are encouraged to check conference website for abstract submission guide at and When submitting an abstract for this session, please select “Multidisciplinary Perspectives on RDS Inference” as the keyword for your presentation. To be extra sure, put a note “Multidisciplinary Perspectives on RDS Inference with Li, Valente and Heimer) in the "additional notes" box on the abstract submission. We are looking forward to your contributions. Email any questions to [log in to unmask], [log in to unmask], [log in to unmask], [log in to unmask].  


_____________________________________________________________________ SOCNET is a service of INSNA, the professional association for social network researchers ( To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.