Respondent-Driven Sampling: An Assessment of Current Methodology

By Krista Gile, Mark S. Handcock. Sociological methodology, 2009

615 citations recorded by the source corpus.

Respondent-driven sampling (RDS) employs a variant of a link-tracing network sampling strategy to collect data from hard-to-reach populations. By tracing the links in the underlying social network, the process exploits the social structure to expand the sample and reduce its dependence on the initial (convenience) sample. The current estimators of population averages make strong assumptions in order to treat the data as a probability sample. We evaluate three critical sensitivities of the estimators: (1) to bias induced by the initial sample, (2) to uncontrollable features of respondent behavior, and (3) to the without-replacement structure of sampling. Our analysis indicates: (1) that the convenience sample of seeds can induce bias, and the number of sample waves typically used in RDS is likely insufficient for the type of nodal mixing required to obtain the reputed asymptotic unbiasedness; (2) that preferential referral behavior by respondents leads to bias; (3) that when a substantial fraction of the target population is sampled the current estimators can have substantial bias. This paper sounds a cautionary note for the users of RDS. While current RDS methodology is powerful and clever, the favorable statistical properties claimed for the current estimates are shown to be heavily dependent on often unrealistic assumptions. We recommend ways to improve the methodology.

Subfields: Epidemiology, General Health Professions, Infectious Diseases

View Paper: https://www.semanticscholar.org/paper/917ecb3f5be57dd09f5d46b24ae7a86fc7dc37ff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Epidemiology

In General Health Professions

In Infectious Diseases

Citations in the corpus

Summary Report of the AAPOR Task Force on Non-probability Sampling (2013, background): “Treating an RDS sample as a probability sample requires further assumptions, and even with these assumptions the variance of resulting RDS estimators can be quite high (Gile and Handcock 2010).”
The effect of differential recruitment, non-response and non-recruitment on estimators for respondent-driven sampling (2010, methodology): “However, these estimators also are also subject to more instability, and have larger variance and greater bias than the VH- or SS- estimators under many other sample conditions, both in this paper, and as described in Gile and Handcock (2010).”
SNOWBALL VERSUS RESPONDENT-DRIVEN SAMPLING (2011, methodology): “The literature is now expanding in several directions, including sensitivity analyses to assess the effects of violations of its assumptions (Gile and Handcock 2010), development of new estimators which may prove more reliable and valid than current estimators, applying the method to a greater range”
Assessing respondent-driven sampling (2010, background): “Recently, Gile and Handcock (13) have evaluated the bias of RDS estimates on more realistic synthetic networks.”
On the Concept of Snowball Sampling (2011, methodology): “ that makes RDS a fruitful area for ongoing research. RDS pairs the practical implementation of a convenience sample with the hope of recovering “something like” a probability sample. Gile (2008) and Gile and Handcock (2010) are the ﬁrst works to systematically evaluate the statistical properties of”
Inference for Nonprobability Samples (2017, background): “If some restrictive assumptions on how the recruiting is done are satisfied, probabilities of being included in a sample can be computed and used for inferences to a full rare population, but these assumptions can easily be violated (e.g., see Gile and Handcock, 2010).”