Homogeneity pursuit and variable selection in regression models for multivariate abundance data.

When building regression models for multivariate abundance data in ecology, it is important to allow for the fact that the species are correlated with each other. Moreover, there is often evidence species exhibit some degree of homogeneity in their responses to each environmental predictor, and that most species are informed by only a subset of predictors. We propose a generalized estimating equation (GEE) approach for simultaneous homogeneity pursuit (ie, grouping species with similar coefficient values while allowing differing groups for different covariates) and variable selection in regression models for multivariate abundance data. Using GEEs allows us to straightforwardly account for between-response correlations through a (reduced-rank) working correlation matrix. We augment the GEE with both adaptive fused lasso- and adaptive lasso-type penalties, which aim to cluster the species-specific coefficients within each covariate and encourage differing levels of sparsity across the covariates, respectively. Numerical studies demonstrate the strong finite sample performance of the proposed method relative to several existing approaches for modeling multivariate abundance data. Applying the proposed method to presence-absence records collected along the Great Barrier Reef in Australia reveals both a substantial degree of homogeneity and sparsity in species-environmental relationships. We show this leads to a more parsimonious model for understanding the environmental drivers of seabed biodiversity, and results in stronger out-of-sample predictive performance relative to methods that do not accommodate such features.

The use of generalized linear mixed models to investigate postmortem lipids in textiles.

Human remains are oftentimes located with textile materials, making them a ubiquitous source of physical evidence. Human remains are also frequently discovered in outdoor environments, increasing the exposure to scavenging activity and soft-tissue decomposition. In such cases, postmortem interval (PMI) estimations can be challenging for investigators when attempting to use traditional methods for reconstructive purposes. Lipid analysis is an emerging area of research in forensic taphonomy, with recent works demonstrating success with the detection and monitoring of lipids over time. In this work, generalized linear mixed models (GLMMs) were utilized to perform rigorous statistical analyses on 30 lipid outcomes in combination with accumulated-degree-days (ADD). The results of this study were consistent with recent works, indicating oleic and palmitic acids to be the most suitable lipids in textiles to target for future use as soft-tissue biomarkers of human decomposition. Interspecies differences between humans and pigs were also addressed in this work.

Screening methods for linear errors-in-variables models in high dimensions.

Microarray studies, in order to identify genes associated with an outcome of interest, usually produce noisy measurements for a large number of gene expression features from a small number of subjects. One common approach to analyzing such high-dimensional data is to use linear errors-in-variables (EIV) models; however, current methods for fitting such models are computationally expensive. In this paper, we present two efficient screening procedures, namely, corrected penalized marginal screening (PMSc) and corrected sure independence screening (SISc), to reduce the number of variables for final model building. Both screening procedures are based on fitting corrected marginal regression models relating the outcome to each contaminated covariate separately, which can be computed efficiently even with a large number of features. Under mild conditions, we show that these procedures achieve screening consistency and reduce the number of features substantially, even when the number of covariates grows exponentially with sample size. In addition, if the true covariates are weakly correlated, we show that PMSc can achieve full variable selection consistency. Through a simulation study and an analysis of gene expression data for bone mineral density of Norwegian women, we demonstrate that the two new screening procedures make estimation of linear EIV models computationally scalable in high-dimensional settings, and improve finite sample estimation and selection performance compared with estimators that do not employ a screening stage.

Assuming independence in spatial latent variable models: Consequences and implications of misspecification.

Multivariate spatial data, where multiple responses are simultaneously recorded across spatially indexed observational units, are routinely collected in a wide variety of disciplines. For example, the Southern Ocean Continuous Plankton Recorder survey collects records of zooplankton communities in the Indian sector of the Southern Ocean, with the aim of identifying and quantifying spatial patterns in biodiversity in response to environmental change. One increasingly popular method for modeling such data is spatial generalized linear latent variable models (GLLVMs), where the correlation across sites is captured by a spatial covariance function in the latent variables. However, little is known about the impact of misspecifying the latent variable correlation structure on inference of various parameters in such models. To address this gap in the literature, we investigate how misspecifying and assuming independence for the latent variables' correlation structure impacts estimation and inference in spatial GLLVMs. Through both theory and numerical studies, we show that performance of maximum likelihood estimation and inference on regression coefficients under misspecification depends on a combination of the response type, the magnitude of true regression coefficient, and the corresponding loadings, and, most importantly, whether the corresponding covariate is (also) spatially correlated. On the other hand, estimation and inference of truly nonzero loadings and prediction of latent variables is consistently not robust to misspecification of the latent variable correlation structure.

Generalized Matrix Factorization: efficient algorithms for fitting generalized linear latent variable models to large data arrays.

Unmeasured or latent variables are often the cause of correlations between multivariate measurements, which are studied in a variety of fields such as psychology, ecology, and medicine. For Gaussian measurements, there are classical tools such as factor analysis or principal component analysis with a well-established theory and fast algorithms. Generalized Linear Latent Variable models (GLLVMs) generalize such factor models to non-Gaussian responses. However, current algorithms for estimating model parameters in GLLVMs require intensive computation and do not scale to large datasets with thousands of observational units or responses. In this article, we propose a new approach for fitting GLLVMs to high-dimensional datasets, based on approximating the model using penalized quasi-likelihood and then using a Newton method and Fisher scoring to learn the model parameters. Computationally, our method is noticeably faster and more stable, enabling GLLVM fits to much larger matrices than previously possible. We apply our method on a dataset of 48,000 observational units with over 2,000 observed species in each unit and find that most of the variability can be explained with a handful of factors. We publish an easy-to-use implementation of our proposed fitting algorithm.

Successional syndromes of saplings in tropical secondary forests emerge from environment-dependent trait-demography relationships.

Identifying generalisable processes that underpin population dynamics is crucial for understanding successional patterns. While longitudinal or chronosequence data are powerful tools for doing so, the traditional focus on community-level shifts in taxonomic and functional composition rather than species-level trait-demography relationships has made generalisation difficult. Using joint species distribution models, we demonstrate how three traits-photosynthetic rate, adult stature, and seed mass-moderate recruitment and sapling mortality rates of 46 woody species during secondary succession. We show that the pioneer syndrome emerges from higher photosynthetic rates, shorter adult statures and lighter seeds that facilitate exploitation of light in younger secondary forests, while 'long-lived pioneer' and 'late successional' syndromes are associated with trait values that enable species to persist in the understory or reach the upper canopy in older secondary forests. Our study highlights the context dependency of trait-demography relationships, which drive successional shifts in sapling's species composition in secondary forests.

Positive interspecific associations consistent with social information use shape juvenile fish assemblages.

Social information obtained from heterospecifics can enhance individual fitness by reducing environmental uncertainty, making it an important driver of mixed-species grouping behavior. Heterospecific groups are well documented among fishes, yet are notably more prevalent among juveniles than more advanced life stages, implying that the adaptive value of joining other species is greater during this developmental period. We propose this phenomenon can be explained by the heightened ecological relevance of heterospecifically produced cues pertaining to predation risk and or resources, as body-size uniformity inherent in early ontogeny yields greater overlap in predator and prey guild membership across juveniles of disparate taxa. To evaluate the putative role of information in shaping juvenile fish assemblages, we employed a joint species distribution model (JSDM), identifying nonrandom relationships among fishes collected in 785 seine hauls within the shallow littoral zones of a subtropical island. After accounting for species-environment relationships, which explained 39% of observed covariation in the abundance of 11 taxa, we detected high rates of positive association (84% of significant correlations) predominantly between mutual foraging guild members, consistent with assemblage patterns predicted to evolve under widespread interspecific information use. Affiliations occurred primarily between species characterized by neutral (i.e., noninteracting) or negative (i.e., predator-prey) relationships in later life stages, supporting the notion that heightened niche overlap due to body size homogeneity acted to increase the pertinence of information among juveniles. Taxa exerted varying degrees of influence on assemblage structure; however Eucinostomus spp., a gregarious generalist with exceptional information-production potential, had an effect several times that of all other species combined, further evidencing the likely role of information in motivating observed relationships. Co-occurrence and qualitative behavioral data inferred from remote underwater video surveys reinforced these conclusions. Collectively, these results suggest that positive interactions linked to information exchange can be among the principal factors organizing juvenile fish assemblages at local scales, highlighting the role of ontogeny in mediating the relevance and exploitation of information across species.

Joint species distribution models with species correlations and imperfect detection.

Spatiotemporal patterns in biological communities are typically driven by environmental factors and species interactions. Spatial data from communities are naturally described by stacking models for all species in the community. Two important considerations in such multispecies or joint species distribution models (JSDMs) are measurement errors and correlations between species. Up to now, virtually all JSDMs have included either one or the other, but not both features simultaneously, even though both measurement errors and species correlations may be essential for achieving unbiased inferences about the distribution of communities and species co-occurrence patterns. We developed two presence-absence JSDMs for modeling pairwise species correlations while accommodating imperfect detection: one using a latent variable and the other using a multivariate probit approach. We conducted three simulation studies to assess the performance of our new models and to compare them to earlier latent variable JSDMs that did not consider imperfect detection. We illustrate our models with a large Atlas data set of 62 passerine bird species in Switzerland. Under a wide range of conditions, our new latent variable JSDM with imperfect detection and species correlations yielded estimates with little or no bias for occupancy, occupancy regression coefficients, and the species correlation matrix. In contrast, with the multivariate probit model we saw convergence issues with large data sets (many species and sites) resulting in very long run times and larger errors. A latent variable model that ignores imperfect detection produced correlation estimates that were consistently negatively biased, that is, underestimated. We found that the number of latent variables required to represent the species correlation matrix adequately may be much greater than previously suggested, namely around n/2, where n is community size. The analysis of the Swiss passerine data set exemplifies how not accounting for imperfect detection will lead to negative bias in occupancy estimates and to attenuation in the estimated covariate coefficients in a JSDM. Furthermore, spatial heterogeneity in detection may cause spurious patterns in the estimated species correlation matrix if not accounted for. Our new JSDMs represent an important extension of current approaches to community modeling to the common case where species presence-absence cannot be detected with certainty.

Efficient estimation of generalized linear latent variable models.

Generalized linear latent variable models (GLLVM) are popular tools for modeling multivariate, correlated responses. Such data are often encountered, for instance, in ecological studies, where presence-absences, counts, or biomass of interacting species are collected from a set of sites. Until very recently, the main challenge in fitting GLLVMs has been the lack of computationally efficient estimation methods. For likelihood based estimation, several closed form approximations for the marginal likelihood of GLLVMs have been proposed, but their efficient implementations have been lacking in the literature. To fill this gap, we show in this paper how to obtain computationally convenient estimation algorithms based on a combination of either the Laplace approximation method or variational approximation method, and automatic optimization techniques implemented in R software. An extensive set of simulation studies is used to assess the performances of different methods, from which it is shown that the variational approximation method used in conjunction with automatic optimization offers a powerful tool for estimation.

Reliably discriminating stock structure with genetic markers: Mixture models with robust and fast computation.

Delineating naturally occurring and self-sustaining subpopulations (stocks) of a species is an important task, especially for species harvested from the wild. Despite its central importance to natural resource management, analytical methods used to delineate stocks are often, and increasingly, borrowed from superficially similar analytical tasks in human genetics even though models specifically for stock identification have been previously developed. Unfortunately, the analytical tasks in resource management and human genetics are not identical-questions about humans are typically aimed at inferring ancestry (often referred to as "admixture") rather than breeding stocks. In this article, we argue, and show through simulation experiments and an analysis of yellowfin tuna data, that ancestral analysis methods are not always appropriate for stock delineation. In this work, we advocate a variant of a previously introduced and simpler model that identifies stocks directly. We also highlight that the computational aspects of the analysis, irrespective of the model, are difficult. We introduce some alternative computational methods and quantitatively compare these methods to each other and to established methods. We also present a method for quantifying uncertainty in model parameters and in assignment probabilities. In doing so, we demonstrate that point estimates can be misleading. One of the computational strategies presented here, based on an expectation-maximization algorithm with judiciously chosen starting values, is robust and has a modest computational cost.

Order selection and sparsity in latent variable models via the ordered factor LASSO.

Generalized linear latent variable models (GLLVMs) offer a general framework for flexibly analyzing data involving multiple responses. When fitting such models, two of the major challenges are selecting the order, that is, the number of factors, and an appropriate structure for the loading matrix, typically a sparse structure. Motivated by the application of GLLVMs to study marine species assemblages in the Southern Ocean, we propose the Ordered Factor LASSO or OFAL penalty for order selection and achieving sparsity in GLLVMs. The OFAL penalty is the first penalty developed specifically for order selection in latent variable models, and achieves this by using a hierarchically structured group LASSO type penalty to shrink entire columns of the loading matrix to zero, while ensuring that non-zero loadings are concentrated on the lower-order factors. Simultaneously, individual element sparsity is achieved through the use of an adaptive LASSO. In conjunction with using an information criterion which promotes aggressive shrinkage, simulation shows that the OFAL penalty performs strongly compared with standard methods and penalties for order selection, achieving sparsity, and prediction in GLLVMs. Applying the OFAL penalty to the Southern Ocean marine species dataset suggests the available environmental predictors explain roughly half of the total covariation between species, thus leading to a smaller number of latent variables and increased sparsity in the loading matrix compared to a model without any covariates.

Uncovering the drivers of host-associated microbiota with joint species distribution modelling.

In addition to the processes structuring free-living communities, host-associated microbiota are directly or indirectly shaped by the host. Therefore, microbiota data have a hierarchical structure where samples are nested under one or several variables representing host-specific factors, often spanning multiple levels of biological organization. Current statistical methods do not accommodate this hierarchical data structure and therefore cannot explicitly account for the effect of the host in structuring the microbiota. We introduce a novel extension of joint species distribution models (JSDMs) which can straightforwardly accommodate and discern between effects such as host phylogeny and traits, recorded covariates such as diet and collection site, among other ecological processes. Our proposed methodology includes powerful yet familiar outputs seen in community ecology overall, including (a) model-based ordination to visualize and quantify the main patterns in the data; (b) variance partitioning to assess how influential the included host-specific factors are in structuring the microbiota; and (c) co-occurrence networks to visualize microbe-to-microbe associations.

Plant community composition and species richness in the High Arctic tundra: From the present to the future.

Arctic plant communities are altered by climate changes. The magnitude of these alterations depends on whether species distributions are determined by macroclimatic conditions, by factors related to local topography, or by biotic interactions. Our current understanding of the relative importance of these conditions is limited due to the scarcity of studies, especially in the High Arctic. We investigated variations in vascular plant community composition and species richness based on 288 plots distributed on three sites along a coast-inland gradient in Northeast Greenland using a stratified random design. We used an information theoretic approach to determine whether variations in species richness were best explained by macroclimate, by factors related to local topography (including soil water) or by plant-plant interactions. Latent variable models were used to explain patterns in plant community composition. Species richness was mainly determined by variations in soil water content, which explained 35% of the variation, and to a minor degree by other variables related to topography. Species richness was not directly related to macroclimate. Latent variable models showed that 23.0% of the variation in community composition was explained by variables related to topography, while distance to the inland ice explained an additional 6.4 %. This indicates that some species are associated with environmental conditions found in only some parts of the coast-inland gradient. Inclusion of macroclimatic variation increased the model's explanatory power by 4.2%. Our results suggest that the main impact of climate changes in the High Arctic will be mediated by their influence on local soil water conditions. Increasing temperatures are likely to cause higher evaporation rates and alter the distribution of late-melting snow patches. This will have little impact on landscape-scale diversity if plants are able to redistribute locally to remain in areas with sufficient soil water.

Flow-diverter in radiation-induced skull base carotid blowout syndrome: do not write it off!

Post-radiotherapy carotid blowout syndrome (CBS) of the skull base is a rare but often catastrophic complication of head and neck malignancies. The existing literature on the treatment of this condition with flow-diverting devices (FDD) is extremely limited and disappointing. We present a case of impending CBS in a patient previously irradiated for nasopharyngeal cancer that was successfully treated with use of multiple FDDs, adjunctive endonasal packing and delayed reinforcement with pedicled naso-septal flap, yielding an excellent outcome at 14-months follow-up. Notwithstanding the discouraging results in literature, our anecdotal experience suggests that endovascular reconstruction using FDD could be an option with long-term viability in post-radiotherapy CBS involving the skull base when reinforced with a vascularised naso-septal flap.

The Effect of Seasonal Ambient Temperatures on Fire-Stimulated Germination of Species with Physiological Dormancy: A Case Study Using Boronia (Rutaceae).

Dormancy and germination requirements determine the timing and magnitude of seedling emergence, with important consequences for seedling survival and growth. Physiological dormancy is the most widespread form of dormancy in flowering plants, yet the seed ecology of species with this dormancy type is poorly understood in fire-prone vegetation. The role of seasonal temperatures as germination cues in these habitats is often overlooked due to a focus on direct fire cues such as heat shock and smoke, and little is known about the combined effects of multiple fire-related cues and environmental cues as these are seldom assessed in combination. We aimed to improve understanding of the germination requirements of species with physiological dormancy in fire-prone floras by investigating germination responses across members of the Rutaceae from south eastern Australia. We used a fully factorial experimental design to quantify the individual and combined effects of heat shock, smoke and seasonal ambient temperatures on germination of freshly dispersed seeds of seven species of Boronia, a large and difficult-to-germinate genus. Germination syndromes were highly variable but correlated with broad patterns in seed morphology and phylogenetic relationships between species. Seasonal temperatures influenced the rate and/or magnitude of germination responses in six species, and interacted with fire cues in complex ways. The combined effects of heat shock and smoke ranged from neutral to additive, synergistic, unitive or negative and varied with species, seasonal temperatures and duration of incubation. These responses could not be reliably predicted from the effect of the application of single cues. Based on these findings, fire season and fire intensity are predicted to affect both the magnitude and timing of seedling emergence in wild populations of species with physiological dormancy, with important implications for current fire management practices and for population persistence under climate change.

Plant functional traits have globally consistent effects on competition.

Phenotypic traits and their associated trade-offs have been shown to have globally consistent effects on individual plant physiological functions, but how these effects scale up to influence competition, a key driver of community assembly in terrestrial vegetation, has remained unclear. Here we use growth data from more than 3 million trees in over 140,000 plots across the world to show how three key functional traits--wood density, specific leaf area and maximum height--consistently influence competitive interactions. Fast maximum growth of a species was correlated negatively with its wood density in all biomes, and positively with its specific leaf area in most biomes. Low wood density was also correlated with a low ability to tolerate competition and a low competitive effect on neighbours, while high specific leaf area was correlated with a low competitive effect. Thus, traits generate trade-offs between performance with competition versus performance without competition, a fundamental ingredient in the classical hypothesis that the coexistence of plant species is enabled via differentiation in their successional strategies. Competition within species was stronger than between species, but an increase in trait dissimilarity between species had little influence in weakening competition. No benefit of dissimilarity was detected for specific leaf area or wood density, and only a weak benefit for maximum height. Our trait-based approach to modelling competition makes generalization possible across the forest ecosystems of the world and their highly diverse species composition.

So Many Variables: Joint Modeling in Community Ecology.

Technological advances have enabled a new class of multivariate models for ecology, with the potential now to specify a statistical model for abundances jointly across many taxa, to simultaneously explore interactions across taxa and the response of abundance to environmental variables. Joint models can be used for several purposes of interest to ecologists, including estimating patterns of residual correlation across taxa, ordination, multivariate inference about environmental effects and environment-by-trait interactions, accounting for missing predictors, and improving predictions in situations where one can leverage knowledge of some species to predict others. We demonstrate this by example and discuss recent computation tools and future directions.

Posterior fossa dural arteriovenous fistula presenting clinically as a carotid-cavernous fistula treated by a direct access cavernous sinus approach.

Dural arteriovenous fistulas (dAVFs) represent approximately 10-15% of all cerebral vascular malformations. Although dAVFs can occur anywhere in the brain, they occur most frequently in the cavernous and transverse-sigmoid sinuses. Posterior fossa dAVFs presenting clinically as carotid-cavernous fistulae (CCF) are rarely encountered in clinical practice. We discuss and illustrate an unusual case of a left posterior fossa dAVF that presented clinically with chemosis and early visual impairment, similar to that of CCF. This was subsequently treated by a direct access cavernous sinus approach. We describe the technique used to access the cavernous sinus directly in cases where conventional transvenous and transarterial routes have been exhausted.