In this paper, we introduce the phylogenetic scan test (PhyloScan) for investigating cross-group differences in microbiome compositions using the Dirichlet-tree multinomial (DTM) model. DTM models the microbiome data through a cascade of independent local DMs on the internal nodes of the phylogenetic tree. Each of the local DMs captures the count distributions of a certain number of operational taxonomic units at a given resolution. Since distributional differences tend to occur in clusters along evolutionary lineages, we design a scan statistic over the phylogenetic tree to allow nodes to borrow signal strength from their parents and children. We also derive a formula to bound the tail probability of the scan statistic, and verify its accuracy through simulations. The PhyloScan procedure is applied to the American Gut dataset to identify taxa associated with diet habits. Empirical studies performed on this dataset show that PhyloScan achieves higher testing power in most cases.

In 2015 the US federal government sponsored a dengue forecasting competition using historical case data from Iquitos, Peru and San Juan, Puerto Rico. Competitors were evaluated on several aspects of out-of-sample forecasts including the targets of peak week, peak incidence during that week, and total season incidence across each of several seasons. Our team was one of the winners of that competition, outperforming other teams in multiple targets/locales. In this paper we report on our methodology, a large component of which, surprisingly, ignores the known biology of epidemics at large—for example, relationships between dengue transmission and environmental factors—and instead relies on flexible nonparametric nonlinear Gaussian process (GP) regression fits that “memorize” the trajectories of past seasons, and then “match” the dynamics of the unfolding season to past ones in real-time. Our phenomenological approach has advantages in situations where disease dynamics are less well understood, or where measurements and forecasts of ancillary covariates like precipitation are unavailable, and/or where the strength of association with cases are as yet unknown. In particular, we show that the GP approach generally outperforms a more classical generalized linear (autoregressive) model (GLM) that we developed to utilize abundant covariate information. We illustrate variations of our method(s) on the two benchmark locales alongside a full summary of results submitted by other contest competitors.

Camera trapping surveys frequently capture individuals whose identity is only known from a single flank. The most widely used methods for incorporating these partial identity individuals into density analyses discard some of the partial identity capture histories, reducing precision, and, while not previously recognized, introducing bias. Here, we present the spatial partial identity model (SPIM), which uses the spatial location where partial identity samples are captured to probabilistically resolve their complete identities, allowing all partial identity samples to be used in the analysis. We show that the SPIM outperforms other analytical alternatives. We then apply the SPIM to an ocelot data set collected on a trapping array with double-camera stations and a bobcat data set collected on a trapping array with single-camera stations. The SPIM improves inference in both cases and, in the ocelot example, individual sex is determined from photographs used to further resolve partial identities—one of which is resolved to near certainty. The SPIM opens the door for the investigation of trapping designs that deviate from the standard two camera design, the combination of other data types between which identities cannot be deterministically linked, and can be extended to the problem of partial genotypes.

Mark-recapture distance sampling is a promising method for surveying bird populations from aircraft in open landscapes. However, commonly available distance sampling estimators require that distances to target animals are made without error and that animals are stationary while sampling is being conducted. Motivated by a recent bird survey where these requirements were routinely violated, we describe a marginal likelihood framework for estimating abundance from double-observer data that can accommodate movement and measurement error when observations are made consecutively (as with front and rear observers), when animals are uniformly distributed during detection by the first observer, and when detections consist of both moving and stationary animals. Assuming that all animals are subject to measurement error and that some animals can move between detections, we integrate over unknown animal locations to construct a marginal likelihood for detection, movement, and measurement error parameters. Estimates of animal abundance are then obtained using a modified Horvitz–Thompson-like estimator. In addition, unmodelled heterogeneity in detection probability can be accommodated through observer dependence parameters. Using simulation, we show that our approach yields low bias compared to approaches that ignore movement and/or measurement error, including in cases where there is considerable detection heterogeneity. Applying our approach to data from a double-observer waterfowl helicopter survey in northern Canada, we are able to estimate bird density accounting for movement and measurement error and corrected for observer heterogeneity. Our approach appears promising for generating unbiased estimates of bird abundance necessary for reliable conservation and management.

In exploratory data analysis, we are often interested in identifying promising pairwise associations for further analysis while filtering out weaker ones. This can be accomplished by computing a measure of dependence on all variable pairs and examining the highest-scoring pairs, provided the measure of dependence used assigns similar scores to equally noisy relationships of different types. This property, called equitability and previously formalized, can be used to assess measures of dependence along with the power of their corresponding independence tests and their runtime.

Here we present an empirical evaluation of the equitability, power against independence, and runtime of several leading measures of dependence. These include the two recently introduced and simultaneously computable statistics ${\mbox{MIC}_{e}}$, whose goal is equitability, and ${\mbox{TIC}_{e}}$, whose goal is power against independence.

Regarding equitability, our analysis finds that ${\mbox{MIC}_{e}}$ is the most equitable method on functional relationships in most of the settings we considered. Regarding power against independence, we find that ${\mbox{TIC}_{e}}$ and Heller and Gorfine’s ${S^{\mathrm{DDP}}}$ share state-of-the-art performance, with several other methods achieving excellent power as well. Our analyses also show evidence for a trade-off between power against independence and equitability consistent with recent theoretical work. Our results suggest that a fast and useful strategy for achieving a combination of power against independence and equitability is to filter relationships by ${\mbox{TIC}_{e}}$ and then to rank the remaining ones using ${\mbox{MIC}_{e}}$. We confirm our findings on a set of data collected by the World Health Organization.

Propensity score matching and weighting are popular methods when estimating causal effects in observational studies. Beyond the assumption of unconfoundedness, however, these methods also require the model for the propensity score to be correctly specified. The recently proposed covariate balancing propensity score (CBPS) methodology increases the robustness to model misspecification by directly optimizing sample covariate balance between the treatment and control groups. In this paper, we extend the CBPS to a continuous treatment. We propose the covariate balancing generalized propensity score (CBGPS) methodology, which minimizes the association between covariates and the treatment. We develop both parametric and nonparametric approaches and show their superior performance over the standard maximum likelihood estimation in a simulation study. The CBGPS methodology is applied to an observational study, whose goal is to estimate the causal effects of political advertisements on campaign contributions. We also provide open-source software that implements the proposed methods.

Large, high-dimensional datasets containing different types of variables are becoming increasingly common. For exploring such data, there is a need for integrated methods. For example, a single genomic experiment can contain large quantities of different types of data (including clinical data) that make it a challenge to coherently describe the patterns of variability within and between the inter-related datasets. Mutual information (MI) is a widely used information theoretic dependency measure that also can identify nonlinear and nonmonotonic associations. First, we develop a computationally efficient implementation of MI between a discrete and a continuous variable. This implementation allows us to apply a coherent approach to all comparisons arising from continuous and categorical data. As commonly applied, MI can have high levels of bias. So we present a novel development of mutual information (MI) that reduces the bias, and that we term bias corrected mutual information (BCMI). Further, BCMI is useful as an association measure that can be incorporated in subsequent analyses such as clustering and visualisation procedures.

To demonstrate our approach, a genomic dataset is re-examined. This dataset contains single nucleotide polymorphisms (SNPs, a discrete variable), gene expression levels and clinical data (all continuous variables). Our approach allows us to integrate these different types of data by exploring associations both within and between these types of variables.

It has recently been reported that adjustment of nonconfounding covariates in case-control genetic association analyses may lead to decreased power when the phenotype is rare. This observation contrasts a well-known result for clinical trials where adjustment of baseline variables always leads to increased power for testing randomized treatment effects. In this paper, we propose a unified solution that guarantees increased power through covariate adjustment regardless of whether the phenotype is rare or common. Our method exploits external phenotype prevalence data through a profile likelihood function, and can be applied to fit any commonly used penetrance models including the logistic and probit regression models. Through extensive simulation studies, we showed empirically that the power of our method was indeed higher than available analysis strategies with or without covariate adjustment, and can be considerably higher when the phenotype was common and the covariate effect was strong. We applied the proposed method to analyze a case-control genetic association study on human high density lipoprotein cholesterol level.

Longitudinal studies play a prominent role in biological, social, and behavioral sciences. Repeated measurements over time facilitate the study of an outcome level, how individuals change over time, and the factors that may impact either or both. A standard approach to modeling childhood growth over time is to use multilevel or mixed effects models to study factors that might play a role in the level and growth over time. However, there has been increased interest in using mixture models, which have inherent grouping structure to more flexibly explain heterogeneity in the longitudinal outcomes, to study growth patterns. While several possible model specifications can be used, these methods generally fail to explicitly group individuals by the shape of their growth pattern separate from level, and thus fail to shed light on the relationships between growth pattern and potential explanatory factors. We illustrate the weaknesses of these methods as they are currently being used. We also propose a pre-processing step that removes the outcome level to focus explicitly on shape, discuss its impact on estimation, and demonstrate its usefulness though a simulation study and with real longitudinal data.

This paper considers the dependence between weather events, for example, rainfall or snow-melt, and the number of water-related property insurance claims. Weather events which cause severe damages are of general interest; decision makers want to take efficient actions against them while the insurance companies want to set adequate premiums. The modelling is challenging since the underlying dynamics vary across geographical regions due to differences in topology, construction designs and climate. We develop new methodology to improve the existing models which fail to model high numbers of claims. The statistical framework is based on both mixture and extremal mixture modelling, with the latter being based on a discretized generalized Pareto distribution. Furthermore, we propose a temporal clustering algorithm and derive new covariates which lead to a better understanding of the association between claims and weather events. The modelling of the claims, conditional on the locally observed weather events, both fit the marginal distributions well and capture the spatial dependence between locations. Our methodology is applied to three cities across Norway to demonstrate its benefits.

Extremal dependence between international stock markets is of particular interest in today’s global financial landscape. However, previous studies have shown this dependence is not necessarily stationary over time. We concern ourselves with modeling extreme value dependence when that dependence is changing over time, or other suitable covariate. Working within a framework of asymptotic dependence, we introduce a regression model for the angular density of a bivariate extreme value distribution that allows us to assess how extremal dependence evolves over a covariate. We apply the proposed model to assess the dynamics governing extremal dependence of some leading European stock markets over the last three decades, and find evidence of an increase in extremal dependence over recent years.

Threshold selection is a critical issue for extreme value analysis with threshold-based approaches. Under suitable conditions, exceedances over a high threshold have been shown to follow the generalized Pareto distribution (GPD) asymptotically. In practice, however, the threshold must be chosen. If the chosen threshold is too low, the GPD approximation may not hold and bias can occur. If the threshold is chosen too high, reduced sample size increases the variance of parameter estimates. To process batch analyses, commonly used selection methods such as graphical diagnostics are subjective and cannot be automated. We develop an efficient technique to evaluate and apply the Anderson–Darling test to the sample of exceedances above a fixed threshold. In order to automate threshold selection, this test is used in conjunction with a recently developed stopping rule that controls the false discovery rate in ordered hypothesis testing. Previous attempts in this setting do not account for the issue of ordered multiple testing. The performance of the method is assessed in a large scale simulation study that mimics practical return level estimation. This procedure was repeated at hundreds of sites in the western US to generate return level maps of extreme precipitation.

Conducting vaccine efficacy trials during outbreaks of emerging pathogens poses particular challenges. The “Ebola ça suffit” trial in Guinea used a novel ring vaccination cluster randomized design to target populations at highest risk of infection. Another key feature of the trial was the use of a delayed vaccination arm as a comparator, in which clusters were randomized to immediate vaccination or vaccination 21 days later. This approach, chosen to improve ethical acceptability of the trial, complicates the statistical analysis as participants in the comparison arm are eventually protected by vaccine. Furthermore, for infectious diseases, we observe time of illness onset and not time of infection, and we may not know the time required for the vaccinee to develop a protective immune response. As a result, including events observed shortly after vaccination may bias the per protocol estimate of vaccine efficacy. We provide a framework for approximating the bias and power of any given analysis period as functions of the background infection hazard rate, disease incubation period, and vaccine immune response. We use this framework to provide recommendations for designing standard vaccine efficacy trials and trials with a delayed vaccination comparator. Briefly, narrower analysis periods within the correct window can minimize or eliminate bias but may suffer from reduced power. Designs should be reasonably robust to misspecification of the incubation period and time to develop a vaccine immune response.

This paper presents a regularized regression model with a two-level structural sparsity penalty applied to locate individual atoms in a noisy scanning transmission electron microscopy image (STEM). In crystals, the locations of atoms is symmetric, condensed into a few lattice groups. Therefore, by identifying the underlying lattice in a given image, individual atoms can be accurately located. We propose to formulate the identification of the lattice groups as a sparse group selection problem. Furthermore, real atomic scale images contain defects and vacancies, so atomic identification based solely on a lattice group may result in false positives and false negatives. To minimize error, model includes an individual sparsity regularization in addition to the group sparsity for a within-group selection, which results in a regression model with a two-level sparsity regularization. We propose a modification of the group orthogonal matching pursuit (gOMP) algorithm with a thresholding step to solve the atom finding problem. The convergence and statistical analyses of the proposed algorithm are presented. The proposed algorithm is also evaluated through numerical experiments with simulated images. The applicability of the algorithm on determination of atom structures and identification of imaging distortions and atomic defects was demonstrated using three real STEM images. We believe this is an important step toward automatic phase identification and assignment with the advent of genomic databases for materials.

Tropical storms are known to be highly chaotic and extremely difficult to predict. In tropical countries such as Singapore, the official lead time for the warnings of heavy storms is usually between 15 and 45 minutes because weather systems develop quickly and are of very short lifespan. A single thunderstorm cell, for example, typically lives for less than an hour. Weather radar echoes, correlated in both space and time, provide a rich source of information for short-term precipitation nowcasting. Based on a large dataset of 276 tropical storms events, this paper investigates a spatio-temporal modeling approach for two-dimensional radar reflectivity (echo) fields. Under a Lagrangian integration scheme, we model the radar reflectivity field by a spatio-temporal conditional autoregressive process with two components. The first component is the dynamic velocity field which determines the motion of the storm, and the second component governs the growth or decay of the returned radar echoes. The proposed method is demonstrated and compared with existing methods using real radar image data collected from a number of 276 tropical storm events from 2010 to 2011 in Singapore. The numerical comparison results show the advantage of the proposed method, in terms of the mean-squared-error, in modeling small-scale localized convective weather systems based on the 77 inter-monsoon season thunderstorm events.

This paper examines a bivariate count time series with some curious statistical features: Saffir–Simpson Category 3 and stronger annual hurricane counts in the North Atlantic and eastern Pacific Ocean Basins. As land and ocean temperatures on our planet warm, an intense climatological debate has arisen over whether hurricanes are becoming more numerous, or whether the strengths of the individual storms are increasing. Recent literature concludes that an increase in hurricane counts occurred in the Atlantic Basin circa 1994. This increase persisted through 2012; moreover, the 1994–2012 period was one of relative inactivity in the eastern Pacific Basin. When Atlantic activity eased in 2013, heavy activity in the eastern Pacific Basin commenced. When examined statistically, a Poisson white noise model for the annual severe hurricane counts is difficult to resoundingly reject. Yet, decadal cycles (longer term dependence) in the hurricane counts is plausible. This paper takes a statistical look at the issue, developing a stationary multivariate count time series model with Poisson marginal distributions and a flexible autocovariance structure. Our auto- and cross-correlations can be negative and have long-range dependence; features that most previous count models cannot achieve in tandem. Our model is new in the literature and is based on categorizing and super-positioning multivariate Gaussian time series. We derive the autocovariance function of the model and propose a method to estimate model parameters. In the end, we conclude that severe hurricane counts are indeed negatively correlated across the two ocean basins. Some evidence for long-range dependence is also presented; however, with only a 49-year record, this issue cannot be definitively judged without additional data.

We propose a statistical space–time model for predicting atmospheric wind speed based on deterministic numerical weather predictions and historical measurements. We consider a Gaussian multivariate space–time framework that combines multiple sources of past physical model outputs and measurements in order to produce a probabilistic wind speed forecast within the prediction window. We illustrate this strategy on wind speed forecasts during several months in 2012 for a region near the Great Lakes in the United States. The results show that the prediction is improved in the mean-squared sense relative to the numerical forecasts as well as in probabilistic scores. Moreover, the samples are shown to produce realistic wind scenarios based on sample spectra and space–time correlation structure.

Gaussian random fields have been one of the most popular tools for analyzing spatial data. However, many geophysical and environmental processes often display non-Gaussian characteristics. In this paper, we propose a new class of spatial models for non-Gaussian random fields on a sphere based on a multi-resolution analysis. Using a special wavelet frame, named spherical needlets, as building blocks, the proposed model is constructed in the form of a sparse random effects model. The spatial localization of needlets, together with carefully chosen random coefficients, ensure the model to be non-Gaussian and isotropic. The model can also be expanded to include a spatially varying variance profile. The special formulation of the model enables us to develop efficient estimation and prediction procedures, in which an adaptive MCMC algorithm is used. We investigate the accuracy of parameter estimation of the proposed model, and compare its predictive performance with that of two Gaussian models by extensive numerical experiments. Practical utility of the proposed model is demonstrated through an application of the methodology to a data set of high-latitude ionospheric electrostatic potentials, generated from the LFM-MIX model of the magnetosphere-ionosphere system.

Wind has the potential to make a significant contribution to future energy resources. Locating the sources of this renewable energy on a global scale is however extremely challenging, given the difficulty to store very large data sets generated by modern computer models. We propose a statistical model that aims at reproducing the data-generating mechanism of an ensemble of runs via a Stochastic Generator (SG) of global annual wind data. We introduce an evolutionary spectrum approach with spatially varying parameters based on large-scale geographical descriptors such as altitude to better account for different regimes across the Earth’s orography. We consider a multi-step conditional likelihood approach to estimate the parameters that explicitly accounts for nonstationary features while also balancing memory storage and distributed computation. We apply the proposed model to more than 18 million points of yearly global wind speed. The proposed SG requires orders of magnitude less storage for generating surrogate ensemble members from wind than does creating additional wind fields from the climate model, even if an effective lossy data compression algorithm is applied to the simulation output.

Next-generation RNA sequencing (RNA-seq) technology has been widely used to assess full-length RNA isoform abundance in a high-throughput manner. RNA-seq data offer insight into gene expression levels and transcriptome structures, enabling us to better understand the regulation of gene expression and fundamental biological processes. Accurate isoform quantification from RNA-seq data is challenging due to the information loss in sequencing experiments. A recent accumulation of multiple RNA-seq data sets from the same tissue or cell type provides new opportunities to improve the accuracy of isoform quantification. However, existing statistical or computational methods for multiple RNA-seq samples either pool the samples into one sample or assign equal weights to the samples when estimating isoform abundance. These methods ignore the possible heterogeneity in the quality of different samples and could result in biased and unrobust estimates. In this article, we develop a method, which we call “joint modeling of multiple RNA-seq samples for accurate isoform quantification” (MSIQ), for more robust isoform quantification by integrating multiple RNA-seq samples under a Bayesian framework. Our method aims to (1) identify a consistent group of samples with homogeneous quality and (2) improve isoform quantification accuracy by jointly modeling multiple RNA-seq samples and allowing for higher weights on the consistent group. We show that MSIQ provides a consistent estimator of isoform abundance, and we demonstrate the accuracy and effectiveness of MSIQ compared with alternative methods through simulation studies on D. melanogaster genes. We justify MSIQ’s advantages over existing approaches via application studies on real RNA-seq data of human embryonic stem cells, brain tissues, and the HepG2 immortalized cell line. We also perform a comprehensive analysis of how the isoform quantification accuracy would be affected by RNA-seq sample heterogeneity and different experimental protocols.

The analysis of human microbiome data is often based on dimension-reduced graphical displays and clusterings derived from vectors of microbial abundances in each sample. Common to these ordination methods is the use of biologically motivated definitions of similarity. Principal coordinate analysis, in particular, is often performed using ecologically defined distances, allowing analyses to incorporate context-dependent, non-Euclidean structure. In this paper, we go beyond dimension-reduced ordination methods and describe a framework of high-dimensional regression models that extends these distance-based methods. In particular, we use kernel-based methods to show how to incorporate a variety of extrinsic information, such as phylogeny, into penalized regression models that estimate taxon-specific associations with a phenotype or clinical outcome. Further, we show how this regression framework can be used to address the compositional nature of multivariate predictors comprised of relative abundances; that is, vectors whose entries sum to a constant. We illustrate this approach with several simulations using data from two recent studies on gut and vaginal microbiomes. We conclude with an application to our own data, where we also incorporate a significance test for the estimated coefficients that represent associations between microbial abundance and a percent fat.

This paper considers testing procedures for screening large genome-wide data, where we examine hundreds of thousands of genetic variants, for example, single nucleotide polymorphisms (SNP), on a quantitative phenotype. We screen the whole genome by SNP sets and propose a new test that is based on conditional effects from multiple SNPs. The test statistic is developed for weak genetic effects and incorporates correlations among genetic variables, which may be very high due to linkage disequilibrium. The limiting null distribution of the test statistic and the power of the test are derived. Under appropriate conditions, the test is shown to be more powerful than the minimum $p$-value method, which is based on marginal SNP effects and is the most commonly used method in genome-wide screening. The proposed test is also compared with other existing methods, including the Higher Criticism (HC) test and the sequence kernel association test (SKAT), through simulations and analysis of a real genome data set. For typical genome-wide data, where effects of individual SNPs are weak and correlations among SNPs are high, the proposed test is more advantageous and clearly outperforms the other methods in the literature.

Accurately evaluating the distribution of genetic ancestry across geographic space is one of the main questions addressed by evolutionary biologists. This question has been commonly addressed through the application of Bayesian estimation programs allowing their users to estimate individual admixture proportions and allele frequencies among putative ancestral populations. Following the explosion of high-throughput sequencing technologies, several algorithms have been proposed to cope with computational burden generated by the massive data in those studies. In this context, incorporating geographic proximity in ancestry estimation algorithms is an open statistical and computational challenge. In this study, we introduce new algorithms that use geographic information to estimate ancestry proportions and ancestral genotype frequencies from population genetic data. Our algorithms combine matrix factorization methods and spatial statistics to provide estimates of ancestry matrices based on least-squares approximation. We demonstrate the benefit of using spatial algorithms through extensive computer simulations, and we provide an example of application of our new algorithms to a set of spatially referenced samples for the plant species Arabidopsis thaliana. Without loss of statistical accuracy, the new algorithms exhibit runtimes that are much shorter than those observed for previously developed spatial methods. Our algorithms are implemented in the R package, tess3r.

Recent advances in technology have enabled the measurement of RNA levels for individual cells. Compared to traditional tissue-level bulk RNA-seq data, single cell sequencing yields valuable insights about gene expression profiles for different cell types, which is potentially critical for understanding many complex human diseases. However, developing quantitative tools for such data remains challenging because of high levels of technical noise, especially the “dropout” events. A “dropout” happens when the RNA for a gene fails to be amplified prior to sequencing, producing a “false” zero in the observed data. In this paper, we propose a Unified RNA-Sequencing Model (URSM) for both single cell and bulk RNA-seq data, formulated as a hierarchical model. URSM borrows the strength from both data sources and carefully models the dropouts in single cell data, leading to a more accurate estimation of cell type specific gene expression profile. In addition, URSM naturally provides inference on the dropout entries in single cell data that need to be imputed for downstream analyses, as well as the mixing proportions of different cell types in bulk samples. We adopt an empirical Bayes’ approach, where parameters are estimated using the EM algorithm and approximate inference is obtained by Gibbs sampling. Simulation results illustrate that URSM outperforms existing approaches both in correcting for dropouts in single cell data, as well as in deconvolving bulk samples. We also demonstrate an application to gene expression data on fetal brains, where our model successfully imputes the dropout genes and reveals cell type specific expression patterns.

Spatio-temporal hierarchical modeling is an extremely attractive way to model the spread of crime or terrorism data over a given region, especially when the observations are counts and must be modeled discretely. The spatio-temporal diffusion is placed, as a matter of convenience, in the process model allowing for straightforward estimation of the diffusion parameters through Bayesian techniques. However, this method of modeling does not allow for the existence of self-excitation, or a temporal data model dependency, that has been shown to exist in criminal and terrorism data. In this manuscript we will use existing theories on how violence spreads to create models that allow for both spatio-temporal diffusion in the process model as well as temporal diffusion, or self-excitation, in the data model. We will further demonstrate how Laplace approximations similar to their use in Integrated Nested Laplace Approximation can be used to quickly and accurately conduct inference of self-exciting spatio-temporal models allowing practitioners a new way of fitting and comparing multiple process models. We will illustrate this approach by fitting a self-exciting spatio-temporal model to terrorism data in Iraq and demonstrate how choice of process model leads to differing conclusions on the existence of self-excitation in the data and differing conclusions on how violence spread spatially-temporally in that country from 2003–2010.

Collaboration networks are thought to be desirable to foster both individual and population productivity. Often programs are implemented to promote collaboration, for example, at academic institutions. However, few tools are available to assess the efficacy of these programs, and very few are data-driven. We carried out a survey at California State University, San Marcos during the 2012–2013 academic year to measure five types of collaboration ties among professors in five science departments at the university over time. During the time period of study, professors participated in NIH-sponsored curriculum development activities with members of other departments. It was hypothesized that participation in these activities would also foster overall collaboration between these departments.

This survey enables the exploration of several methodological and theoretical challenges in network research. In this paper we develop a statistical approach to assess the impact of programmatic interventions on collaboration using model-assisted social network analysis. We derive and implement a hierarchical Bayesian approach to modeling error-prone responses in surveys and examine the effect of an intervention on network structure. Based on this analysis we find an increase in educational collaboration over time after adjusting for the length of time each professor had to form collaborative ties at the university.