Network sampling is used around the world for surveys of vulnerable, hard-to-reach populations including people at risk for HIV, opioid misuse, and emerging epidemics. The sampling methods include tracing social links to add new people to the sample. Current estimates from these surveys are inaccurate, with large biases and mean squared errors and unreliable confidence intervals. New estimators are introduced here which eliminate almost all of the bias, have much lower mean squared error, and enable confidence intervals with good properties. The improvement is attained by avoiding unrealistic assumptions about the population network and the design, instead using the topology of the sample network data together with the sampling design actually used. In simulations using the real network of an at-risk population, the new estimates eliminate almost all the bias and have mean squared-errors that are 2 to 92 times lower than those of current estimators. The new estimators are effective with a wide variety of network designs including those with strongly restricted branching such as Respondent-Driven Sampling and freely branching designs such as Snowball Sampling.
We propose Horvitz-Thompson-like and Hajek-like estimators of the total and mean of the values of a variable of interest associated with the elements of a hard-to-reach population sampled by the variant of link-tracing sampling proposed by Felix-Medina and Thompson (2004). As examples of this type of population are drug users, homeless people and sex workers. In this sampling variant, a frame of venues or places where the members of the population tend to gather, such as parks and bars, is constructed. The frame is not assumed to cover the whole population. An initial cluster sample of element…
This study aims to evaluate the performance of power in the likelihood ratio test for changepoint detection by bootstrap sampling, and proposes a hypothesis test based on bootstrapped confidence interval lengths. Assuming i.i.d normally distributed errors, and using the bootstrap method, the changepoint sampling distribution is estimated. Furthermore, this study describes a method to estimate a data set with no changepoint to form the null sampling distribution. With the null sampling distribution, and the distribution of the estimated changepoint, critical values and power calculations can be…
Snowball designs are the most natural of the network sampling designs. They have many desirable properties for sampling hidden and hard-to reach populations. They have been under-used in recent years because simple design-based estimators and confidence intervals have not been available for them. The needed estimation methods are supplied in this paper. Snowball sampling methods and accurate estimators with them are needed for sampling of the people exposed to the animals from which new coronavirus outbreaks originate, and to sample the animal populations to which they are exposed. Accurate es…
Midzuno sampling enables to estimate ratios unbiasedly. We prove the asymptotic normality for estimators of totals and ratios under Midzuno sampling. We also propose consistent variance estimators.
Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framework for temporal network sampling with unbiased estimation. We develop online, single-pass sampling algorithms and unbiased estimators for temporal network sampling. The proposed algorithms enable fast, accurate, and memory-efficient statistical estimation of temporal network patt…
Active learning can reduce the number of samples needed to perform a hypothesis test and to estimate the parameters of a model. In this paper, we revisit the work of Chernoff that described an asymptotically optimal algorithm for performing a hypothesis test. We obtain a novel sample complexity bound for Chernoff's algorithm, with a non-asymptotic term that characterizes its performance at a fixed confidence level. We also develop an extension of Chernoff sampling that can be used to estimate the parameters of a wide variety of models and we obtain a non-asymptotic bound on the estimation erro…
Informative sampling designs can impact spatial prediction, or kriging, in two important ways. First, the sampling design can bias spatial covariance parameter estimation, which in turn can bias spatial kriging estimates. Second, even with unbiased estimates of the spatial covariance parameters, since the kriging variance is a function of the observation locations, these estimates will vary based on the sample and overestimate the population-based estimates. In this work, we develop a weighted composite likelihood approach to improve spatial covariance parameter estimation under informative sa…
We consider Bayesian inference by importance sampling when the likelihood is analytically intractable but can be unbiasedly estimated. We refer to this procedure as importance sampling squared (IS2), as we can often estimate the likelihood itself by importance sampling. We provide a formal justification for importance sampling when working with an estimate of the likelihood and study its convergence properties. We analyze the effect of estimating the likelihood on the resulting inference and provide guidelines on how to set up the precision of the likelihood estimate in order to obtain an opti…
Consider a population of individuals and a network that encodes social connections among them. We are interested in making inference on finite population and super-population estimands that are a function of both individuals' responses and of the network, from a sample. Neither the sampling frame nor the network are available. However, the sampling mechanism implicitly leverages the network to recruit individuals, thus partially revealing social interactions among the individuals in the sample, as well as their responses. This is a common setting that arises, for instance, in epidemiology and …
Some of the most used sampling mechanisms that implicitly leverage a social network depend on tuning parameters; for instance, Respondent-Driven Sampling (RDS) is specified by the number of seeds and maximum number of referrals. We are interested in the problem of optimizing these sampling mechanisms with respect to their tuning parameters in order to optimize the inference on a population quantity, where such quantity is a function of the network and measurements taken at the nodes. This is done by formulating the problem in terms of decision theory and information theory, in turn. We discuss…
A new strategy is introduced for estimating population size and networked population characteristics. Sample selection is based on a multi-wave snowball sampling design. A generalized stochastic block model is posited for the population's network graph. Inference is based on a Bayesian data augmentation procedure. Applications are provided to an empirical and simulated populations. The results demonstrate that statistically efficient estimates of the size and distribution of the population can be achieved.
Respondent-driven sampling (RDS) is a method of chain referral sampling popular for sampling hidden and/or marginalized populations. As such, even under the ideal sampling assumptions, the performance of RDS is restricted by the underlying social network: if the network is divided into communities that are weakly connected to each other, then RDS is likely to oversample one of these communities. In order to diminish the "referral bottlenecks" between communities, we propose anti-cluster RDS (AC-RDS), an adjustment to the standard RDS implementation. Using a standard model in the RDS literature…
Accurate estimates of subnational health and demographic indicators are critical for informing health policy decisions. Many countries collect relevant data using complex household surveys, but when data are limited, direct survey weighted estimates of small area proportions may be unreliable. Area level models treating these direct estimates as response data can improve precision but often require known sampling variances of the direct estimators for all areas. In practice, the sampling variances are typically estimated, so standard approaches do not account for a key source of uncertainty. I…
Electronic health record (EHR) data are increasingly used for biomedical research, but these data have recognized data quality challenges. Data validation is necessary to use EHR data with confidence, but limited resources typically make complete data validation impossible. Using EHR data, we illustrate prospective, multi-wave, two-phase validation sampling to estimate the association between maternal weight gain during pregnancy and the risks of her child developing obesity or asthma. The optimal validation sampling design depends on the unknown efficient influence functions of regression coe…
We assess the reliability of relational event model parameters estimated under two sampling schemes: (1) uniform sampling from the observed events and (2) case-control sampling which samples non-events, or null dyads ("controls"), from a suitably defined risk set. We experimentally determine the variability of estimated parameters as a function of the number of sampled events and controls per event, respectively. Results suggest that relational event models can be reliably fitted to networks with more than 12 million nodes connected by more than 360 million dyadic events by analyzing a sample …
There is great interest in finding meaningful subgroups of attributed network data. There are many available methods for clustering complete network. Unfortunately, much network data is collected through sampling, and therefore incomplete. Respondent-driven sampling (RDS) is a widely used method for sampling hard-to-reach human populations based on tracing links in the underlying unobserved social network. The resulting data therefore have tree structure representing a sub-sample of the network, along with many nodal attributes. In this paper, we introduce an approach to adjust mixture models …
Statistical estimates from survey samples have traditionally been obtained via design-based estimators. In many cases, these estimators tend to work well for quantities such as population totals or means, but can fall short as sample sizes become small. In today's "information age," there is a strong demand for more granular estimates. To meet this demand, using a Bayesian pseudo-likelihood, we propose a computationally efficient unit-level modeling approach for non-Gaussian data collected under informative sampling designs. Specifically, we focus on binary and multinomial data. Our approach i…
Respondent-driven sampling (RDS) is a link-tracing sampling method that is especially suitable for sampling hidden populations. RDS combines an efficient snowball-type sampling scheme with inferential procedures that yield unbiased population estimates under some assumptions about the sampling procedure and population structure. Several seed individuals are typically used to initiate RDS recruitment. However, standard RDS estimation theory assume that all sampled individuals originate from only one seed. We present an estimator, based on a random walk with teleportation, which accounts for the…
