Respondent-driven Sampling Data Research Articles

Smartphone-based Respondent Driven Sampling (RDS): A methodological advance in surveying small or 'hard-to-reach' populations.

Producing statistically robust profiles of small or ‘hard-to-reach’ populations has always been a challenge for researchers. Since surveying the wider population in order to capture a large enough sample of cases is usually too costly or impractical, researchers have been opting for ‘snowballing’ or ‘time-location sampling’. The former does not allow for claims to representativeness, and the latter struggles with under-coverage and estimating confidence intervals. Respondent Driven Sampling (RDS) is a method that combines snowballing sampling with an analytical algorithm that corrects for biases that arise in snowballing. For all its advantages, a major weakness of RDS has been around data collection. Traditionally done on-site, the process is costly and lengthy. When done online, it is cheaper and faster but under a serious threat from fraud, compromising data quality and validity of findings. This paper describes a real-life application of a RDS data collection system that maximizes fraud prevention while still benefiting from low cost and speedy data collection.

Preserving Multiple Homophilies in a Network Configuration Model.

Respondent-driven sampling (RDS) is a popular method for surveying hidden populations based on friendships and existing social network connections. In such a survey the underlying hidden network remains largely unknown. However, it is useful to estimate its size as well as the relative proportions of surveyed features. The fact that linked network participants are likely to share common features is called homophily, and is an important property in understanding the topology of social networks. In this paper we present a methodology that scales up RDS data to model the underlying hidden population in a way that preserves multiple homophilies among different features. We test our model using 46 features of the population sampled by the SATHCAP RDS survey. Our network generation methodology successfully preserves the homophilic associations in a randomly generated Barabasi-Albert network. Having created a realistic model of the expanded SATHCAP network, we test our model by simulating RDS surveys over it, and comparing the resulting sub-networks with SATHCAP. In our generated network, we preserve 85% of homophilies to under 2% error. In our simulated RDS surveys we preserve 85% of homophilies to under 15% error.

General regression methods for respondent-driven sampling data.

Respondent-driven sampling is a variant of link-tracing sampling techniques that aim to recruit hard-to-reach populations by leveraging individuals’ social relationships. As such, a respondent-driven sample has a graphical component which represents a partially observed network of unknown structure. Moreover, it is common to observe homophily, or the tendency to form connections with individuals who share similar traits. Currently, there is a lack of principled guidance on multivariate modelling strategies for respondent-driven sampling to address peer effects driven by homophily and the dependence between observations within the network. In this work, we propose a methodology for general regression techniques using respondent-driven sampling data. This is used to study the socio-demographic predictors of HIV treatment optimism (about the value of antiretroviral therapy) among gay, bisexual and other men who have sex with men, recruited into a respondent-driven sampling study in Montreal, Canada.

Inferring Bivariate Association from Respondent-driven Sampling Data

Abstract Respondent-driven sampling (RDS) is an effective method of collecting data from many hard-to-reach populations. Valid statistical inference for these data relies on many strong assumptions. In standard samples, we assume observations from pairs of individuals are independent. In RDS, this assumption is violated by the sampling dependence between individuals. We propose a method to semi-parametrically estimate the null distributions of standard test statistics in the presence of sampling dependence, allowing for more valid statistical testing for dependence between pairs of variables within the sample. We apply our method to study characteristics of young adult illicit opioid users in New York City.

Optimizing respondent-driven sampling to find undiagnosed HIV-infected people who inject drugs.

We evaluated whether identification of undiagnosed HIV-infected people who inject drugs (PWID) via respondent-driven sampling (RDS) can be enhanced through a precision RDS (pRDS) approach. First, using prior RDS data from PWID in India, we built a prediction algorithm for recruiting undiagnosed HIV-infected PWID. pRDS was tested in Morinda, Punjab where participants were randomly assigned to standard or pRDS. In the standard RDS approach, all participants received two recruitment coupons. For pRDS, the algorithm determined an individual's probability of recruiting an undiagnosed PWID, and individuals received either two (low probability) or five (high probability) coupons. Efficiency in identifying undiagnosed HIV-infected PWID for the RDS approaches was evaluated in two ways: the number needed to recruit (NNR) and identification rate/week. Predictors of recruiting undiagnosed PWID included HIV/HCV infection, network size, syringe services utilization, and injection environment. 1631 PWID were recruited in Morinda. From the standard RDS approach, 615 were recruited, including 39 undiagnosed; from pRDS, 1012 were recruited, including 77 undiagnosed. In pRDS, those with higher predicted probability were more likely to recruit others with HIV/HCV co-infection, undiagnosed and viremic HIV, and who utilized services. pRDS had a significantly higher identification rate of undiagnosed PWID (1.5/week) compared with the standard (0.8/week). The NNR for pRDS (13.1) was not significantly lower than the standard approach (15.8). pRDS identified twice as many undiagnosed and viremic PWID significantly faster than the standard approach. Leveraging RDS or similar network-based strategies should be considered alongside other strategies to ensure meeting UNAIDS targets.

Estimation of Non-Linear Parameters with Data Collected Using Respondent-Driven Sampling

Respondent-driven sampling (RDS) is a snowball-type sampling method used to survey hidden populations, that is, those that lack a sampling frame. In this work, we consider the problem of regression modeling and association for continuous RDS data. We propose a new sample weight method for estimating non-linear parameters such as the covariance and the correlation coefficient. We also estimate the variances of the proposed estimators. As an illustration, we performed a simulation study and an application to an ethnic example. The proposed estimators are consistent and asymptotically unbiased. We discuss the applicability of the method as well as future research.

Assessing Bias in Population Size Estimates Among Hidden Populations When Using the Service Multiplier Method Combined With Respondent-Driven Sampling Surveys: Survey Study.

BackgroundPopulation size estimates (PSEs) for hidden populations at increased risk of HIV, including female sex workers (FSWs), are important to inform public health policy and resource allocation. The service multiplier method (SMM) is commonly used to estimate the sizes of hidden populations. We used this method to obtain PSEs for FSWs at 9 sites in Zimbabwe and explored methods for assessing potential biases that could arise in using this approach.ObjectiveThis study aimed to guide the assessment of biases that arise when estimating the population sizes of hidden populations using the SMM combined with respondent-driven sampling (RDS) surveys.MethodsWe conducted RDS surveys at 9 sites in late 2013, where the Sisters with a Voice program (the program), which collects program visit data of FSWs, was also present. Using the SMM, we obtained PSEs for FSWs at each site by dividing the number of FSWs who attended the program, based on program records, by the RDS-II weighted proportion of FSWs who reported attending this program in the previous 6 months in the RDS surveys. Both the RDS weighting and SMM make a number of assumptions, potentially leading to biases if the assumptions are not met. To test these assumptions, we used convergence and bottleneck plots to assess seed dependence of RDS-II proportion estimates, chi-square tests to assess if there was an association between the characteristics of FSWs and their knowledge of program existence, and logistic regression to compare the characteristics of FSWs attending the program with those recruited to RDS surveys.ResultsThe PSEs ranged from 194 (95% CI 62-325) to 805 (95% CI 456-1142) across 9 sites from May to November 2013. The 95% CIs for the majority of sites were wide. In some sites, the RDS-II proportion of women who reported program use in the RDS surveys may have been influenced by the characteristics of selected seeds, and we also observed bottlenecks in some sites. There was no evidence of association between characteristics of FSWs and knowledge of program existence, and in the majority of sites, there was no evidence that the characteristics of the populations differed between RDS and program data.ConclusionsWe used a series of rigorous methods to explore potential biases in our PSEs. We were able to identify the biases and their potential direction, but we could not determine the ultimate direction of these biases in our PSEs. We have evidence that the PSEs in most sites may be biased and a suggestion that the bias is toward underestimation, and this should be considered if the PSEs are to be used. These tests for bias should be included when undertaking population size estimation using the SMM combined with RDS surveys.

Abstract C015: Social network analysis with respondent driven sampling data: A study of ethnic and geographic integration on Guam and Hawaii

Abstract US Pacific Islanders are one of the fastest-growing population groups in the US, and serious disparities in health outcomes exist in this group, with cancer being the leading cause of death. Limited knowledge about the cancer communication practices and risk behaviors of US Pacific Islanders, as well as their social network structure and integration, makes effective cancer prevention interventions difficult, and contributes to disparities. In 2017, we conducted a survey on health communication on Guam and Hawaii using the respondent-driven sampling method (RDS) to recruit participants (N=733 for Hawaii, and N=533 for Guam). RDS is a network-based sampling technique where initial seed respondents recruit others from their social networks. The recruiting process repeats iteratively, thereby forming long referral chains. RDS provides a viable data for making inferences about the underlying network structure. During the sampling process two pieces of information are gathered. First, each recruiter-recruit dyad is documented. Second, respondents are asked how many other members of the target population they know and interact with. In this study, we used this information to create recruitment chains and test the quantity and quality of cross-gender, cross-ethnicity, cross-generation ties. We also analyzed the geographic distribution and spatial clustering of the samples. Self-reported network size (degree) was used to estimate of a homophily, a measure of the strength of association to one's own group beyond random mixing. In general, strong homophily was found for different ethnic groups (with values ranging from 0.7 to 0.8), whereas gender and age had weak homophily. Even though the participants tended to recruit spatially proximal peers, both samples in Guam and Hawaii eventually covered the whole catchment area. Citation Format: Grazyna Badowski, Louis Dulana, Lilnabeth P. Somera, Kevin Cassel, Hye-ryeon Lee, Janessa Roman, Jayson Morales. Social network analysis with respondent driven sampling data: A study of ethnic and geographic integration on Guam and Hawaii [abstract]. In: Proceedings of the Eleventh AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2018 Nov 2-5; New Orleans, LA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2020;29(6 Suppl):Abstract nr C015.

Estimation and correction of bias in network simulations based on respondent-driven sampling data

Respondent-driven sampling (RDS) is widely used for collecting data on hard-to-reach populations, including information about the structure of the networks connecting the individuals. Characterizing network features can be important for designing and evaluating health programs, particularly those that involve infectious disease transmission. While the validity of population proportions estimated from RDS-based datasets has been well studied, little is known about potential biases in inference about network structure from RDS. We developed a mathematical and statistical platform to simulate network structures with exponential random graph models, and to mimic the data generation mechanisms produced by RDS. We used this framework to characterize biases in three important network statistics – density/mean degree, homophily, and transitivity. Generalized linear models were used to predict the network statistics of the original network from the network statistics of the sample network and observable sample design features. We found that RDS may introduce significant biases in the estimation of density/mean degree and transitivity, and may exaggerate homophily when preferential recruitment occurs. Adjustments to network-generating statistics derived from the prediction models could substantially improve validity of simulated networks in terms of density, and could reduce bias in replicating mean degree, homophily, and transitivity from the original network.

Correcting for differential recruitment in respondent-driven sampling data using ego-network information

Respondent-Driven sampling (RDS) is a sampling method devised to overcome challenges with sampling hard-to-reach human populations. The sampling starts with a limited number of individuals who are asked to recruit a small number of their contacts. Every surveyed individual is subsequently given the same opportunity to recruit additional members of the target population until a pre-established sample size is achieved. The recruitment process consequently implies that the survey respondents are responsible for deciding who enters the study. Most RDS prevalence estimators assume that participants select among their contacts completely at random. The main objective of this work is to correct the inference for departure from this assumption, such as systematic recruitment based on the characteristics of the individuals or based on the nature of relationships. To accomplish this, we introduce three forms of non-random recruitment, provide estimators for these recruitment behaviors and extend three estimators and their associated variance procedures. The proposed methodology is assessed through a simulation study capturing various sampling and network features. Finally, the proposed methods are applied to a public health setting.

Unweighted regression models perform better than weighted regression techniques for respondent-driven sampling data: results from a simulation study

BackgroundIt is unclear whether weighted or unweighted regression is preferred in the analysis of data derived from respondent driven sampling. Our objective was to evaluate the validity of various regression models, with and without weights and with various controls for clustering in the estimation of the risk of group membership from data collected using respondent-driven sampling (RDS).MethodsTwelve networked populations, with varying levels of homophily and prevalence, based on a known distribution of a continuous predictor were simulated using 1000 RDS samples from each population. Weighted and unweighted binomial and Poisson general linear models, with and without various clustering controls and standard error adjustments were modelled for each sample and evaluated with respect to validity, bias and coverage rate. Population prevalence was also estimated.ResultsIn the regression analysis, the unweighted log-link (Poisson) models maintained the nominal type-I error rate across all populations. Bias was substantial and type-I error rates unacceptably high for weighted binomial regression. Coverage rates for the estimation of prevalence were highest using RDS-weighted logistic regression, except at low prevalence (10%) where unweighted models are recommended.ConclusionsCaution is warranted when undertaking regression analysis of RDS data. Even when reported degree is accurate, low reported degree can unduly influence regression estimates. Unweighted Poisson regression is therefore recommended.

Estimating the Population Size of Female Sex Workers in Namibia Using a Respondent-Driven Sampling Adjustment to the Reverse Tracking Method: A Novel Approach.

BackgroundKey populations, including female sex workers (FSWs), are at a disproportionately high risk for HIV infection. Estimates of the size of these populations serve as denominator data to inform HIV prevention and treatment programming and are necessary for the equitable allocation of limited public health resources.ObjectiveThis study aimed to present the respondent-driven sampling (RDS) adjusted reverse tracking method (RTM; RadR), a novel population size estimation approach that combines venue mapping data with RDS data to estimate the population size, adjusted for double counting and nonattendance biases.MethodsWe used data from a 2014 RDS survey of FSWs in Windhoek and Katima Mulilo, Namibia, to demonstrate the RadR method. Information from venue mapping and enumeration from the survey formative assessment phase were combined with survey-based venue-inquiry questions to estimate population size, adjusting for double counting, and FSWs who do not attend venues. RadR estimates were compared with the official population size estimates, published by the Namibian Ministry of Health and Social Services (MoHSS), and with the unadjusted RTM.ResultsUsing the RadR method, we estimated 1552 (95% simulation interval, SI, 1101-2387) FSWs in Windhoek and 453 (95% SI: 336-656) FSWs in Katima Mulilo. These estimates were slightly more conservative than the MoHSS estimates—Windhoek: 3000 (1800-3400); Katima Mulilo: 800 (380-2000)—though not statistically different. We also found 75 additional venues in Windhoek and 59 additional venues in Katima Mulilo identified by RDS participants’ responses that were not detected during the initial mapping exercise.ConclusionsThe RadR estimates were comparable with official estimates from the MoHSS. The RadR method is easily integrated into RDS studies, producing plausible population size estimates, and can also validate and update key population maps for outreach and venue-based sampling.

Social Network Clustering and the Spread of HIV/AIDS Among Persons Who Inject Drugs in 2 Cities in the Philippines.

The Philippines has seen rapid increases in HIV prevalence among people who inject drugs. We study 2 neighboring cities where a linked HIV epidemic differed in timing of onset and levels of prevalence. In Cebu, prevalence rose rapidly from below 1% to 54% between 2009 and 2011 and remained high through 2013. In nearby Mandaue, HIV remained below 4% through 2011 then rose rapidly to 38% by 2013. We hypothesize that infection prevalence differences in these cities may owe to aspects of social network structure, specifically levels of network clustering. Building on previous research, we hypothesize that higher levels of network clustering are associated with greater epidemic potential. Data were collected with respondent-driven sampling among men who inject drugs in Cebu and Mandaue in 2013. We first examine sample composition using estimators for population means. We then apply new estimators of network clustering in respondent-driven sampling data to examine associations with HIV prevalence. Samples in both cities were comparable in composition by age, education, and injection locations. Dyadic needle-sharing levels were also similar between the 2 cities, but network clustering in the needle-sharing network differed dramatically. We found higher clustering in Cebu than Mandaue, consistent with expectations that higher clustering is associated with faster epidemic spread. This article is the first to apply estimators of network clustering to empirical respondent-driven samples, and it offers suggestive evidence that researchers should pay greater attention to network structure's role in HIV transmission dynamics.

Evaluating Variance Estimators for Respondent-Driven Sampling.

Respondent-Driven Sampling (RDS) is a network-based method for sampling hard-to-reach populations that is widely used by public health agencies and researchers worldwide. Estimation of population characteristics from RDS data is challenging due to the unobserved population network, and multiple point and variance estimators have been proposed. Research evaluating these estimators has been limited and largely focused on point estimation; this analysis is the first evaluation of multiple variance estimators currently in use. We evaluated the performance of RDS variance estimators via simulations of RDS on synthetic networked populations constructed from 40 RDS surveys of injection drug users in the United States. In these simulations, average design effects (DEs) were lower and average 95% confidence interval (CI) coverage percentages were higher than suggested in previous work: typical DE range = 1–3; average 95% CI coverage = 93%. However, DE and CI coverage vary across the 40 sets of simulations, suggesting that the characteristics of a given study should be evaluated to assess estimator performance. We also found that simulation results are sensitive to whether sampling is conducted with replacement and the approach used to create CIs. We conclude that CI coverage rates and DEs are often acceptable but not perfect and that RDS estimates are usually reliable in scenarios where RDS assumptions are met. While RDS estimation performed reasonably well, we found strong evidence that the simple random sample variance estimator and corresponding CIs significantly underestimate variance and should not be used to analyze RDS data.

NEW SURVEY QUESTIONS AND ESTIMATORS FOR NETWORK CLUSTERING WITH RESPONDENT-DRIVEN SAMPLING DATA.

Respondent-driven sampling (RDS) is a popular method for sampling hard-to-survey populations that leverages social network connections through peer recruitment. While RDS is most frequently applied to estimate the prevalence of infections and risk behaviors of interest to public health, such as HIV/AIDS or condom use, it is rarely used to draw inferences about the structural properties of social networks among such populations because it does not typically collect the necessary data. Drawing on recent advances in computer science, we introduce a set of data collection instruments and RDS estimators for network clustering, an important topological property that has been linked to a network's potential for diffusion of information, disease, and health behaviors. We use simulations to explore how these estimators, originally developed for random walk samples of computer networks, perform when applied to RDS samples with characteristics encountered in realistic field settings that depart from random walks. In particular, we explore the effects of multiple seeds, without replacement versus with replacement, branching chains, imperfect response rates, preferential recruitment, and misreporting of ties. We find that clustering coefficient estimators retain desirable properties in RDS samples. This paper takes an important step toward calculating network characteristics using nontraditional sampling methods, and it expands the potential of RDS to tell researchers more about hidden populations and the social factors driving disease prevalence.

Prevalence of STI symptoms and high levels of stigma in STI healthcare among men who have sex with men in Dar es Salaam, Tanzania: a respondent-driven sampling study.

Symptoms of sexually transmitted infections (STIs), whether they are presented for treatment or diagnosis, and how they are received by the clinician where they are presented, may be concomitants of stigma associated with homosexuality in homophobic climates. We analyzed respondent-driven sampling data from a study on 200 young men who have sex with men (MSM) in Dar es Salaam, Tanzania to examine sample prevalence, treatment and clinician response to 10 symptoms potentially associated with STIs. Survey measures included 10 self-reported STI symptoms, further specified according to location (genital, anal, oral), further specified according to place of diagnosis, place of, treatment whether there was pharmacy treatment or self-medication, healthcare worker (HCW) inquiries about source of infection and whether the HCW was polite. Most common symptoms reported were genital pain, burning urination, genital itching/burning, penile discharge, and groin swelling. Anal symptoms had the lowest proportion of treatment at public clinics and among the highest proportion of pharmacy treatment; anal sores had the highest proportion of self-medication. HCWs were reported as not being polite in response to 71-90% of the symptoms, (median = 82%). The findings suggest that stigma and negative HCW response are barriers to public clinic treatment for MSM in Tanzania and that these may have implications for both STI treatment and the HIV cascade.

A single weighting approach to analyze respondent-driven sampling data.

Background and objectives:Respondent-driven sampling (RDS) is widely used to sample hidden populations and RDS data are analyzed using specially designed RDS analysis tool (RDSAT). RDSAT estimates parameters such as proportions. Analysis with RDSAT requires separate weight assignment for individual variables even in a single individual; hence, regression analysis is a problem. RDS-analyst is another advanced software that can perform three methods of estimates, namely, successive sampling method, RDS I and RDS II. All of these are in the process of refinement and need special skill to perform analysis. We propose a simple approach to analyze RDS data for comprehensive statistical analysis using any standard statistical software.Methods:We proposed an approach (RDS-MOD - respondent driven sampling-modified) that determines a single normalized weight (similar to RDS II of Volz-Heckathorn) for each participant. This approach converts the RDS data into clustered data to account the pre-existing relationship between recruits and the recruiters. Further, Taylor's linearization method was proposed for calculating confidence intervals for the estimates. Generalized estimating equation approach was used for regression analysis and parameter estimates of different software were compared.Results:The parameter estimates such as proportions obtained by our approach were matched with those from currently available special software for RDS data.Interpretation & conclusions:The proposed weight was comparable to different weights generated by RDSAT. The estimates were comparable to that by RDS II approach. RDS-MOD provided an efficient and easy-to-use method of estimation and regression accounting inter-individual recruits’ dependence.

Estimating the Size of Hidden Populations Using Respondent-driven Sampling Data: Case Examples from Morocco.

Respondent-driven sampling is used worldwide to estimate the population prevalence of characteristics, such as HIV/AIDS and associated risk factors in hard-to-reach populations. Estimating the total size of these populations is of great interest to national and international organizations; however, reliable measures of population size often do not exist. Successive sampling-population size estimation (SS-PSE) along with network size imputation allows population size estimates to be made without relying on separate studies or additional data (as in network scale-up, multiplier, and capture-recapture methods), which may be biased. Ten population size estimates were calculated for people who inject drugs, female sex workers, men who have sex with other men, and migrants from sub-Saharan Africa in six different cities in Morocco. SS-PSE estimates fell within or very close to the likely values provided by experts and the estimates from previous studies using other methods. SS-PSE is an effective method for estimating the size of hard-to-reach populations that leverages important information within respondent-driven sampling studies. The addition of a network size imputation method helps to smooth network sizes allowing for more accurate results. However, caution should be used particularly when there is reason to believe that clustered subgroups may exist within the population of interest or when the sample size is small in relation to the population.

If you are not counted, you don't count: Estimating the number of African-American Men who have Sex with Men in San Francisco.

International Journal of Epidemiology, 2015, Vol. 44, Supplement 1 i39 Risky Behaviors: Free Papers Abstract #: 2474 If you are not counted, you don’t count: Estimating the number of African-American Men who have Sex with Men in San Francisco. P. D. Wesson, BA 1 , M. S. Handcock, PhD 2 , W. McFarland, PhD 3,4 and H. F. Raymond, DrPH 3,4 University of California, Berkeley, Berkeley, CA, USA, 2 University of California, Los Angeles, Los Angeles, CA, USA, 3 University of California, San Francisco, San Francisco, CA, USA, 4 San Francisco Department of Public Health, San Francisco, CA, USA Downloaded from http://ije.oxfordjournals.org/ by guest on October 25, 2016 INTRODUCTION: The HIV epidemic has disproportionately affected African-American (AA) men who have sex with men (MSM). Resource allocation for programs targeting key populations such as AA MSM require reliable estimates of their numbers. Current population size estimation (PSE) methods rely on assump- tions that are difficult to meet, potentially producing large biases. METHODS: We applied a new method to estimate the number of AA MSM in San Francisco (SF) using a respondent-driven sampling (RDS) survey. The approach uses respondents’ self-reported network size (i.e. the number of other AA MSM known to them in SF), along with a specification of the prior knowledge about the population size, to model the total size of the target population based on their proba- bility of recruitment. A Bayesian approach is used to quantify the amount of information on population size available in the survey. The plausibility of the resulting estimate was corroborated against an inde- pendent estimate of all MSM in SF and HIV case reporting data. RESULTS: 259 AA MSM were recruited in the RDS survey. The method calculated a median of 6,230 AA MSM living in SF (95% CI 1,984–35,545). The prevalence of diagnosed HIV in the survey (17.3%) projects 1,078 known HIV cases among AA MSM, compa- rable to the 1,170 actually reported to city’s surveillance system. A previous independent survey estimating 66,487 total MSM in SF, 6.1% AA, estimates 4055 AA MSM. CONCLUSIONS: The new method produced a robust, plausible, and consistent population size estimate for AA MSM. Given that RDS surveys are frequently done in many hidden populations world- wide, the method provides a simple, appealing tool to rapidly pro- duce estimates of the size of high risk populations – a fundamental public health measure that has been scarce for much of the HIV epi- demic. It is a useful complement to existing methods, especially when only RDS data are available.

Condom use among immigrant Latino sexual minorities: multilevel analysis after respondent-driven sampling.

This study explored correlates of condom use within a respondent-driven sample of 190 Spanish-speaking immigrant Latino sexual minorities, including gay and bisexual men, other men who have sex with men (MSM), and transgender person, in North Carolina. Five analytic approaches for modeling data collected using respondent-driven sampling (RDS) were compared. Across most approaches, knowledge of HIV and sexually transmitted infections (STIs) and increased condom use self-efficacy predicted consistent condom use and increased homophobia predicted decreased consistent condom use. The same correlates were not significant in all analyses but were consistent in most. Clustering due to recruitment chains was low, while clustering due to recruiter was substantial. This highlights the importance accounting for clustering when analyzing RDS data.