Social network analysis with respondent-driven sampling data: A study of racial integration on campus

This paper presents respondent-driven sampling (RDS) as a viable method of sampling and analyzing social networks with survey data. RDS is a network based sampling and analysis method that provides a middle ground compliment to ego-centric and saturated methods of social network analysis. The method provides survey data, similar to ego-centric approaches, on individuals who are connected by behaviorally documented ties, allowing for macro-level analysis of network structure, similar to that supported by saturated approaches. Using racial interaction of university undergraduates as an empirical example, the paper examines whether and to what extent racial diversity at the institutional level is reflected as racial integration at the interpersonal level by testing hypotheses regarding the quantity and quality of cross-race friendships. The primary goal of this article, however, is to introduce RDS to the network community and to stimulate further research toward the goal of expanding the analytical capacity of RDS. Advantages, limitations, and areas for future research to network analysis using RDS are discussed.     

Community understanding of respondent-driven sampling in a medical research setting in Uganda: importance for the use of RDS for public health research

Respondent-driven sampling (RDS) is a widely-used variant of snowball sampling. Respondents are selected not from a sampling frame, but from a social network of existing members of the sample. Incentives are provided for participation and for the recruitment of others. Ethical and methodological criticisms have been raised about RDS. In this study RDS was used to recruit male household heads in rural Uganda. We investigated community members' understanding and experience of the method, and explored how these may have affected the quality of the RDS survey data. Our findings suggest that because participants recruit participants, the use of RDS in medical research may result in increased difficulties in gaining informed consent, and data collected using RDS may be particularly susceptible to bias due to differences in the understanding of key concepts between researchers and members of the community.     

Comparing the effectiveness of respondent-driven sampling and quota sampling in migration research

We evaluate the effectiveness in empirical migration research of the respondent-driven sampling (RDS) and the quota sampling with regard to four criteria: quality of the data; sociometric diversity of the sample; geographic coverage of the sample; and cost-effectiveness. We review two surveys of ex-USSR migrants, conducted simultaneously in the Warsaw metropolitan area, each undertaken with the use of one of the two sampling methods. We find that although the RDS was considerably costlier, it enabled faster data collection and posed a lower risk of underestimating the cost of the survey. We also find that the RDS generated higher-quality data, and that it was more successful in surveying short-term circular migrants. This comparative evaluation contributes to the literature on social research methods in that it links the sampling methods with the quality and character of the data, and helps assess the usefulness and applicability of RDS in empirical migration studies.     

EXTENSIONS OF RESPONDENT-DRIVEN SAMPLING: ANALYZING CONTINUOUS VARIABLES AND CONTROLLING FOR DIFFERENTIAL RECRUITMENT

Respondent-driven sampling (RDS) is a network-based method for sampling hidden and hard-to-reach populations that has been shown to produce asymptotically unbiased population estimates when its assumptions are satisfied. This includes resolving a major concern regarding bias in chain-referral samples—that is, producing a population estimate that is independent of the seeds (initial subjects) with which sampling began. However, RDS estimates are limited to nominal variables, and one of the assumptions required for the proof of lack of bias is the absence of differential recruitment. One aim of this paper is to analyze the role of differential recruitment, quantify the bias it produces, and propose a new estimator that controls for it. The second aim is to extend RDS so that it can be employed to analyze continuous variables in a manner that controls for differential recruitment. The third aim is to describe means for carrying out multivariate analyses using RDS data. The analyses employ data from an RDS sample of 264 jazz musicians in the greater New York metropolitan area, taken in 2002.     

Linked Ego Networks: Improving estimate reliability and validity with respondent-driven sampling

Respondent-driven sampling (RDS) is currently widely used for the study of HIV/AIDS-related high risk populations. However, recent studies have shown that traditional RDS methods are likely to generate large variances and may be severely biased since the assumptions behind RDS are seldom fully met in real life. To improve estimation in RDS studies, we propose a new method to generate estimates with ego network data, which is collected by asking respondents about the composition of their personal networks, such as “what proportion of your friends are married?”. By simulations on an extracted real-world social network of gay men as well as on artificial networks with varying structural properties, we show that the precision of estimates for population characteristics is greatly improved. The proposed estimator shows superior advantages over traditional RDS estimators, and most importantly, the method exhibits strong robustness to the recruitment preference of respondents and degree reporting error, which commonly happen in RDS practice and may generate large estimate biases and errors for traditional RDS estimators. The positive results henceforth encourage researchers to collect ego network data for variables of interests by RDS, for both hard-to-access populations and general populations when random sampling is not applicable.     

AN EMPIRICAL TEST OF RESPONDENT-DRIVEN SAMPLING: POINT ESTIMATES, VARIANCE, DEGREE MEASURES, AND OUT-OF-EQUILIBRIUM DATA

This paper, which is the first large-scale application of respondent-driven sampling (RDS) to nonhidden populations, tests three factors related to RDS estimation against institutional data using two WebRDS samples of university undergraduates. First, two methods of calculating RDS point estimates are compared. RDS estimates calculated using both methods coincide closely, but variance estimation, especially for small groups, is problematic for both methods. In one method, the bootstrap algorithm used to generate confidence intervals is found to underestimate variance. In the other method, where analytical variance estimation is possible, confidence intervals tend to overestimate variance. Second, RDS estimates are found to be robust against varying measures of individual degree. Results suggest the standard degree measure currently employed in most RDS studies is among the best-performing degree measures. Finally, RDS is found to be robust against the inclusion of out-of-equilibrium data. The results show that valid point estimates can be generated with RDS analysis using real data, but that further research is needed to improve variance estimation techniques.     

Assessing respondent-driven sampling: A simulation study across different networks

The purpose was to assess RDS estimators in populations simulated with diverse connectivity characteristics, incorporating the putative influence of misreported degrees and transmission processes. Four populations were simulated using different random graph models. Each population was “infected” using four different transmission processes. From each combination of population x transmission, one thousand samples were obtained using a RDS-like sampling strategy. Three estimators were used to predict the population-level prevalence of the “infection”. Several types of misreported degrees were simulated. Also, samples were generated using the standard random sampling method and the respective prevalence estimates, using the classical frequentist estimator. Estimation biases in relation to population parameters were assessed, as well as the variance. Variability was associated with the connectivity characteristics of each simulated population. Clustered populations yield greater variability and no RDS-based strategy could address the estimation biases. Misreporting degrees had modest effects, especially when RDS estimators were used. The best results for RDS-based samples were observed when the “infection” was randomly attributed, without any relation with the underlying network structure.     

Bias decomposition and estimator performance in respondent-driven sampling

Respondent-Driven Sampling (RDS) is a method of network sampling that is used to sample hard-to-reach populations. The resultant sample is non-random, but different weighting methods can account for the over-sampling of (1) high-degree individuals and (2) homophilous groups that recruit members more effectively. While accounting for degree-bias is almost universally agreed upon, accounting for recruitment-bias has been debated as it can further increase estimate variance without substantially reducing bias. Simulation-based research has examined which weighting procedures perform best given underlying population network structures, group recruitment differences, and sampling processes. Yet, in the field, analysts do not have a priori knowledge of the network they are sampling. We show that the RDS sample data itself can determine whether a degree-based estimator is sufficient. Formulas derived from the decomposition of a ‘dual-component’ estimator can approximate the ‘recruitment component’ (RC) and ‘degree component’ (DC) of a sample’s bias. Simulations show that RC and DC values can predict the performance of different classes of estimators. Samples with extreme ‘RC’ values, a consequence of network homophily and differential recruitment, are better served by a classical estimator. The use of sample data to improve estimator selection is a promising innovation for RDS, as the population network features that should guide estimator selection are typically unknown.     

Lesbian, gay, and bisexual homeless youth: an eight-city public health perspective

This article reports on results of a one-day public health survey conducted in six states by homeless youth providers to measure and compare risk factors between lesbian, gay, and bisexual (LGB) homeless youth and non-LGB homeless youth. This article intends to inform the child welfare field on existing gaps in services and areas where more training and technical support is necessary in providing services to homeless LGB youth. The findings point to substantial differences within the homeless youth sample and demonstrate that in addition to the public health risks young people face merely by being homeless, the risks are exacerbated for those who self-identify as lesbian, gay, or bisexual. The article informs child welfare providers and policymakers about the substantial vulnerability of LGB youth beyond that of non-LGB homeless youth and the need to fund programming, training, technical assistance and further research to specifically respond to the complex needs of this population.     

“I’m not homeless,I’m houseless”: identifying as homeless and associations with service utilization among Los Angeles homeless young people

Little is known about homeless young people’s identification of being homeless and how that identity may or may not be associated with service utilization. This study of 444 homeless young people attending Los Angeles area drop-in centers explores the associations of demographic characteristics, homelessness characteristics, negative lifetime experiences, mental health symptoms, technology use, and past month service utilization with identifying as homeless. Fifty-two percent of the sample identified as being homeless. Being Black, a current traveler, and history of injection drug use were all significantly associated with a decreased likelihood in identifying as homeless. However, having fair/poor health, accessing shelter services, and reporting one’s own substance use as a reason for homelessness were all significantly associated with identifying as homeless. There are important service implications for reaching young people who are in need of services but may not identify with the target population label of homeless.     

The discourse and dimensions of irregularity in post-apartheid South Africa

South Africa's migration policy since 1994 has been described as contradictory and confused. Indeed, there are profound differences of opinion within government and civil society over the best means to deal with what is believed to be a massive and threatening increase in clandestine migration and irregular employment.
Clarity of thought and policy debate has been hampered by an inflammatory discourse which fixates on the issue of numbers, and views all migrants as a problem and threat. Partly this reflects fundamental inadequacies in systems of data collection and analysis, and partly a poor understanding of the causes and character of cross-border migration in Southern Africa.
As a corrective, this article presents an overview of the causes and spatial/sectoral distribution of irregular employment in post-apartheid South Africa, drawing on recent research. It then critically examines efforts to ascertain the dimensions of undocumented migration to South Africa, concluding that the results are fundamentally flawed by the methodologies used. The article then disaggregates irregular migration and assesses current knowledge about each subcategory.
In conclusion, the article argues for a comprehensive labour market survey as the foundation for a coordinated and rational approach to the challenges of irregular migration and employment.     

A long road ahead: A progress report on educating homeless children and youth in america

The plight of contemporary homelessness in American society has been well documented, including the growth in homeless families with school age homeless children and independent homeless youth. The impact of homelessness on schools and schooling has resulted in a school-age population with complex problems for which no simple solutions exist. This article chronicles the progress made in recent years in addressing the educational needs of homeless children and youth in America and notes particular areas of concern that remain to be solved if education is to hold a meaningful place in their disrupted lives. Specifically, concerns regarding awareness and perceptions of homelessness, early childhood educational needs, intervention with special populations, interagency collaboration in service delivery, and the need for comprehensive evaluations of homeless education efforts are discussed. Additionally, suggestions for improving policy and practice salient to educating homeless students are offered     

Health Issues of Homeless Youth

The purpose of this paper is to provide an overview of what is currently known about the health issues of homeless youth, focusing on risk-taking behaviors, health status, and access to care. The paper addresses the health issues of homeless youth in the U.S. within an international context. Existing data suggest that homeless adolescents exhibit high rates of risk-taking behaviors, face additional barriers to access of health care, and suffer from a high burden of poor health. However, most research on the health of homeless youth has been cross-sectional and has relied on convenience sampling. Future research should focus on conducting more methodologically rigorous studies on the specific health needs of homeless youth. Research should include eliciting information directly from the youth about their preferred health care interventions.     

Sampling and Estimation in Hidden Populations Using Respondent‐Driven Sampling

Standard statistical methods often provide no way to make accurate estimates about the characteristics of hidden populations such as injection drug users, the homeless, and artists. In this paper, we further develop a sampling and estimation technique called respondent‐driven sampling, which allows researchers to make asymptotically unbiased estimates about these hidden populations. The sample is selected with a snowball‐type design that can be done more cheaply, quickly, and easily than other methods currently in use. Further, we can show that under certain specified (and quite general) conditions, our estimates for the percentage of the population with a specific trait are asymptotically unbiased. We further show that these estimates are asymptotically unbiased no matter how the seeds are selected. We conclude with a comparison of respondent‐driven samples of jazz musicians in New York and San Francisco, with corresponding institutional samples of jazz musicians from these cities. The results show that some standard methods for studying hidden populations can produce misleading results.     

The Healthy Young Men's Study: Sampling Methods to Recruit a Random Cohort of Young Men Who Have Sex With Men

Recruiting a scientifically sound cohort of young men who have sex with men (YMSM) is an enduring research challenge. The few cohort studies that have been conducted to date on YMSM have relied on nonprobability sampling methods to construct their cohorts. While these studies have provided valuable information about HIV risk behaviors among YMSM, their generalizability to broader YMSM populations is limited. In this article, the authors describe a venue-based sampling methodology used to recruit a large and diverse cohort of YMSM from public venues in Los Angeles County, California. Venue-based sampling is a multistage probability sampling design that uses standard outreach techniques and standard survey methods to systematically enumerate, sample, and survey hard-to-reach populations. The study design allowed the authors to estimate individual, familial, and interpersonal psychosocial factors associated with HIV risk and health-seeking behaviors for a cohort of YMSM with known properties. Study participants completed an extensive baseline survey and over a 2-year period completed four follow-up surveys at 6-month intervals. The baseline survey was administered in both English and Spanish.     

CRACKING THE CORNFIELDS: Recruiting Illicit Stimulant Drug Users in Rural Ohio

This article describes the process of recruiting research subjects for a natural history study of illicit stimulant use in rural Ohio using respondent-driven sampling and ethnographic methods. Participant observation, qualitative interviews, and focus groups were used to establish the project and to evaluate and modify the sampling process as it unfolded. We outline the steps taken in several different rural counties, using ethnographic data to illustrate local differences and obstacles that were faced. The article concludes that respondent-driven sampling is a promising method for identifying and recruiting members of hidden populations in rural areas. However, adequate time must be allotted to establish ethnographic footholds and to reach various networks in separate communities.     

On the Edge of Homelessness: Rural Poverty and Housing Insecurity1

Abstract Homelessness in rural America is a problem hardly recognized, little understood, and only minimally studied by rural sociologists. This article, based on long-term field research in upstate New York, sets the problem of rural homelessness in context, explains the increase in rural poverty that puts more people at risk of homelessness, and examines some trends in rural housing that reduce the ability of poorer residents to secure adequate shelter. The nature of housing insecurity and the strategies poor rural people use to keep themselves from becoming literally homeless are noted. Interviews and questionnaires conducted among insecurely-housed low-income people and interviews and records supplied by agencies and institutions serving the poor provide the information on which arguments are based. The conclusion is that the definition of homelessness should be broadened for rural usage to encompass poor people on the edge of or at high risk of homelessness; also, programs to assist the homeless and prevent homelessness must be appropriate for rural situations.     

Respondent-Driven Sampling: An Assessment of Current Methodology

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: to bias induced by the initial sample, to uncontrollable features of respondent behavior, and 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.