Respondent Driven Sampling
by Janet Salmons, PhD., Research Community Manager for SAGE Methodspace
What is Respondent-Driven Sampling (RDS)?
The Encyclopedia of Survey Research Methods describes it as:
Respondent-driven sampling (RDS) is a method for drawing probability samples of "hidden," or alternatively, hard-to-reach, populations. Populations such as these are difficult to sample using standard survey research methods for two reasons: First, they lack a sampling frame, that is, an exhaustive list of population members from which the sample can be drawn. Second, constructing a sampling frame is not feasible because one or more of the following are true: (a) The population is such a small part of the general population that locating them through a general population survey would be prohibitively costly; (b) because the population has social networks that are difficult for outsiders to penetrate, access to the population requires personal contacts; and (c) membership in the population is stigmatized, so gaining access requires establishing trust. Populations with these characteristics are important to many research areas, including arts and culture (e.g. jazz musicians and aging artists), public policy (e.g. immigrants and the homeless), and public health (e.g. drug users and commercial sex workers).
RDS accesses members of hidden populations through their social networks, employing a variant of a snowball (i.e. chain-referral) sampling. As in all such samples, the study begins with a set of initial respondents who serve as "seeds." These then recruit their acquaintances, friends, or relatives who qualify for inclusion in the study to form the first "wave." The first wave respondents then recruit the second wave, who in turn recruit the third wave, and so forth. The sample expands in this manner, growing wave by wave, in the manner of a snowball increasing in size as it rolls down a hill.
RDS then combines snowball sampling—a non-probability sampling technique—with a mathematical model that weights the sample to compensate for the fact that it was not obtained in a simple random way. (pp. 740 -741)
How can it be used? This multidisciplinary collection of open-access articles offers some examples.
Heckathorn, D. (Ed.) (2008). . (Vols. 1-0). Sage Publications, Inc., https://doi.org/10.4135/9781412963947
Abdul-Quader, A.S., Heckathorn, D.D., Sabin, K. et al. Implementation and Analysis of Respondent Driven Sampling: Lessons Learned from the Field. J Urban Health 83 (Suppl 1), 1–5 (2006). https://doi.org/10.1007/s11524-006-9108-8
Those who engage in illegal or stigmatized behaviors, which put them at risk of HIV infection, are largely concentrated in urban centers. Owing to their illegal and/or stigmatized behaviors, they are difficult to reach with public health surveillance and prevention programs.1 These populations include illicit drug users, sex workers and men who have sex with men. Development and implementation of adequate prevention services targeting hidden populations requires data on risk behaviors and disease prevalence from non-biased samples. In the last two decades, a number of sampling methods have been used to collect risk behavior and disease prevalence data from highly at-risk populations and to direct survey participants to prevention services. These include venue-based time–space sampling, targeted sampling, and snowball sampling.
Hequembourg, A. L., & Panagakis, C. (2019). Maximizing respondent-driven sampling field procedures in the recruitment of sexual minorities for health research. SAGE Open Medicine, 7, 2050312119829983. https://doi.org/10.1177/2050312119829983
Research to address the significant health burden experienced by sexual minority populations remains hampered by a lack of appropriate sampling methods to support evidence-based studies. Respondent-driven sampling offers one viable strategy to recruit these hidden populations. Because few studies systematically report their experiences using respondent-driven sampling to recruit sexual minorities, this article aligns with recent recommendations for the standardization of reporting and transparency in studies utilizing respondent-driven sampling. We (1) provide detailed descriptions about the successful execution of respondent-driven sampling in two community-based studies of sexual minority individuals, (2) outline procedures to enhance the effectiveness of respondent-driven sampling referral processes, (3) present mixed-methods results regarding the effectiveness of respondent-driven sampling in our studies, and (4) offer recommendations for other researchers when using respondent-driven sampling.
Johnston, L. G., & Sabin, K. (2010). Sampling Hard-to-Reach Populations with Respondent Driven Sampling. Methodological Innovations Online, 5(2), 38-48. https://doi.org/10.4256/mio.2010.0017
Cost effective and targeted prevention, intervention and treatment programs for hard-to-reach populations at risk for HIV and other infections rely on the collection of quality data through biological and behavioral surveillance surveys (BBSS). Over the past decade, there has been a global expansion of BBSS to measure the prevalence of HIV and other infections, and related risk behaviors among injecting drug users, males who have sex with males, and female sex workers. However, a major challenge to sampling these hard-to-reach populations is that they are usually stigmatised and/or practice illegal behaviors which, in turn, make them difficult to access and unwilling to participate in research efforts. Over the past decade, respondent driven sampling (RDS) has become recognised as a viable option for rigorous sampling of hard-to-reach populations. This paper introduces RDS methods and describes some of the advantages and challenges to implementing and analysing surveys that use RDS.
Léon, L., Des Jarlais, D., Jauffret-Roustide, M., & Le Strat, Y. (2016). Update on respondent-driven sampling: Theory and practical considerations for studies of persons who inject drugs. Methodological Innovations, 9, 2059799116672878. https://doi.org/10.1177/2059799116672878
In the last 5 years, more than 600 articles using respondent-driven sampling has been published. This article aims to provide an overview of this sampling technique with an update on the key questions that remain when using respondent-driven sampling, with regard to its application and estimators. Respondent-driven sampling was developed by Heckathorn in 1997 and was based on the principle of individuals recruiting other individuals, who themselves were recruited in previous waves. When there is no sampling frame, respondent-driven sampling has demonstrated its ability to capture individuals belonging to “hidden” or “hard-to-reach” populations in numerous epidemiological surveys. People who use drugs, sex workers, or men who have sex with men are notable examples of specific populations studied using this technique, particularly by public agencies such as the Centers for Disease Control and Prevention in the United States. Respondent-driven sampling, like many others, is based on a set of assumptions that, when respected, can ensure an unbiased estimator. Based on a literature review, we will discuss, among other topics, the effect of violating these assumptions. A special focus is made on surveys of persons who inject drugs. Publications show two major thrusts—methodological and applied researches—for providing practical recommendations in conducting respondent-driven sampling studies. The reasons why respondent-driven sampling did not work for a given population of interest will usually provide important insights for designing health-promoting interventions for that population.
McCreesh, N., Copas, A., Seeley, J., Johnston, L. G., Sonnenberg, P., Hayes, R. J., ... & White, R. G. (2013). Respondent driven sampling: determinants of recruitment and a method to improve point estimation. PLoS One, 8(10), e78402.
Respondent-driven sampling (RDS) is a variant of a link-tracing design intended for generating unbiased estimates of the composition of hidden populations that typically involves giving participants several coupons to recruit their peers into the study. RDS may generate biased estimates if coupons are distributed non-randomly or if potential recruits present for interview non-randomly. We explore if biases detected in an RDS study were due to either of these mechanisms, and propose and apply weights to reduce bias due to non-random presentation for interview.
Schonlau, M., & Liebau, E. (2012). Respondent-Driven Sampling. The Stata Journal, 12(1), 72-93. https://doi.org/10.1177/1536867x1201200106
Respondent-driven sampling is a network sampling technique typically employed for hard-to-reach populations (for example, drug users, men who have sex with men, people with HIV). Similarly to snowball sampling, initial seed respondents recruit additional respondents from their network of friends. The recruiting process repeats iteratively, thereby forming long referral chains. Unlike in snowball sampling, it is crucial to obtain estimates of respondents’ personal network sizes (that is, number of acquaintances in the target population) and information about who recruited whom. Markov chain theory makes it possible to derive population estimates and sampling weights. We introduce a new Stata command for respondent-driven sampling and illustrate its use.
Semaan, S. (2010). Time-Space Sampling and Respondent-Driven Sampling with Hard-to-Reach Populations. Methodological Innovations Online, 5(2), 60-75. https://doi.org/10.4256/mio.2010.0019
Time-space sampling (TSS; also referred to as time-location sampling, TLS) and respondent-driven sampling (RDS) are strategies that can be used for sampling hard-to-reach populations, for whom it is difficult to construct a sampling frame of the individual members of the population. With proper planning, execution, weighting, and analysis of relevant sampling-related data, both strategies have the potential to produce samples that are representative of the target populations. TSS is a probability-based strategy for recruiting members of a target population congregating at specific locations and times. RDS is predicated on the recognition that project participants are better able than project staff to locate and refer to the study site other potential participants; peers from the target population with whom they have an established relationship. Capture-recapture analysis can incorporate TSS and RDS data to estimate the size of a hard-to-reach population. TSS and RDS have been used extensively around the world in public health projects with populations at high risk for HIV infection. The collective experience gained from using TSS and RDS in HIV-related projects can be valuable in using these sampling strategies with other hard-to-reach populations in projects related to economics, political science, or sociology. Although TSS and RDS have specific strengths and limitations in terms of their abilities to produce valid results that enhance generalizability of findings, the choice of a particular sampling strategy depends on characteristics of the target population and the goal and resources of the project. Proper planning, monitoring, and evaluation of the sampling strategy and attention to logistical, regulatory, and ethical considerations are important to the successful implementation and effectiveness of the sampling strategy.
More Methodspace posts about sampling and recruiting participants
How do decide what literature you need for a review? See this post featuring an interview Martin Hiebl and related open-access article about sample selection.