Towards novel approaches to modelling biotic interactions in multispecies assemblages at large spatial extents

Aim Biotic interactions – within guilds or across trophic levels – have widely been ignored in species distribution models (SDMs). This synthesis outlines the development of ‘species interaction distribution models’ (SIDMs), which aim to incorporate multispecies interactions at large spatial extents using interaction matrices. Location Local to global. Methods We review recent approaches for extending classical SDMs to incorporate biotic interactions, and identify some methodological and conceptual limitations. To illustrate possible directions for conceptual advancement we explore three principal ways of modelling multispecies interactions using interaction matrices: simple qualitative linkages between species, quantitative interaction coefficients reflecting interaction strengths, and interactions mediated by interaction currencies. We explain methodological advancements for static interaction data and multispecies time series, and outline methods to reduce complexity when modelling multispecies interactions. Results Classical SDMs ignore biotic interactions and recent SDM extensions only include the unidirectional influence of one or a few species. However, novel methods using error matrices in multivariate regression models allow interactions between multiple species to be modelled explicitly with spatial co‐occurrence data. If time series are available, multivariate versions of population dynamic models can be applied that account for the effects and relative importance of species interactions and environmental drivers. These methods need to be extended by incorporating the non‐stationarity in interaction coefficients across space and time, and are challenged by the limited empirical knowledge on spatio‐temporal variation in the existence and strength of species interactions. Model complexity may be reduced by: (1) using prior ecological knowledge to set a subset of interaction coefficients to zero, (2) modelling guilds and functional groups rather than individual species, and (3) modelling interaction currencies and species’ effect and response traits. Main conclusions There is great potential for developing novel approaches that incorporate multispecies interactions into the projection of species distributions and community structure at large spatial extents. Progress can be made by: (1) developing statistical models with interaction matrices for multispecies co‐occurrence datasets across large‐scale environmental gradients, (2) testing the potential and limitations of methods for complexity reduction, and (3) sampling and monitoring comprehensive spatio‐temporal data on biotic interactions in multispecies communities.     

Factors influencing soay sheep survival: a Bayesian analysis

This article presents a Bayesian analysis of mark-recapture-recovery data on Soay sheep. A reversible jump Markov chain Monte Carlo technique is used to determine age classes of common survival, and to model the survival probabilities in those classes using logistic regression. This involves environmental and individual covariates, as well as random effects. Auxiliary variables are used to impute missing covariates measured on individual sheep. The Bayesian approach suggests different models from those previously obtained using classical statistical methods. Following model averaging, features that were not previously detected, and which are of ecological importance, are identified.     

Spatial synchrony in stream fish populations: influence of species traits

Spatial synchrony in population dynamics has been identified in most taxonomic groups. Numerous studies have reported varying levels of spatial synchrony among closely‐related species, suggesting that species' characteristics may play a role in determining the level of synchrony. However, few studies have attempted to relate this synchrony to the ecological characteristics and/or life‐history traits of species. Yet, as to some extent the extinction risk may be related to synchrony patterns, identifying a link between species' characteristics and spatial synchrony is crucial, and would help us to define effective conservation planning. Here, we investigated whether species attributes and temperature synchrony (i.e. a proxy of the Moran effect) account for the differences in spatial population synchrony observed in 27 stream fish species in France. After measuring and testing the level of synchrony for each species, we performed a comparative analysis to detect the phylogenetic signal of these levels, and to construct various multi‐predictor models with species traits and temperature synchrony as covariates, while taking phylogenetic relatedness into account. We then performed model averaging on selected models to take model uncertainty into account in our parameter estimates. Fifteen of the 27 species displayed a significant level of synchrony. Synchrony was weak, but highly variable between species, and was not conserved across the phylogeny. We found that some species' characteristics significantly influenced synchrony levels. Indeed, the average model indicated that species associated with greater dispersal abilities, lower thermal tolerance, and opportunistic strategy displayed a higher degree of synchrony. These findings indicate that phylogeny and spatial temperature synchrony do not provide information pertinent for explaining the variations in species' synchrony levels, whereas the dispersal abilities, the life‐history strategies and the upper thermal tolerance limits of species do appear to be quite reliable predictors of synchrony levels.     

Analyzing complex capture-recapture data in the presence of individual and temporal covariates and model uncertainty

SUMMARY: We consider the issue of analyzing complex ecological data in the presence of covariate information and model uncertainty. Several issues can arise when analyzing such data, not least the need to take into account where there are missing covariate values. This is most acutely observed in the presence of time-varying covariates. We consider mark-recapture-recovery data, where the corresponding recapture probabilities are less than unity, so that individuals are not always observed at each capture event. This often leads to a large amount of missing time-varying individual covariate information, because the covariate cannot usually be recorded if an individual is not observed. In addition, we address the problem of model selection over these covariates with missing data. We consider a Bayesian approach, where we are able to deal with large amounts of missing data, by essentially treating the missing values as auxiliary variables. This approach also allows a quantitative comparison of different models via posterior model probabilities, obtained via the reversible jump Markov chain Monte Carlo algorithm. To demonstrate this approach we analyze data relating to Soay sheep, which pose several statistical challenges in fully describing the intricacies of the system.     

Ecological correlates of the spatial co‐occurrence of sympatric mammalian carnivores worldwide

The composition of local mammalian carnivore communities has far‐reaching effects on terrestrial ecosystems worldwide. To better understand how carnivore communities are structured, we analysed camera trap data for 108 087 trap days across 12 countries spanning five continents. We estimate local probabilities of co‐occurrence among 768 species pairs from the order Carnivora and evaluate how shared ecological traits correlate with probabilities of co‐occurrence. Within individual study areas, species pairs co‐occurred more frequently than expected at random. Co‐occurrence probabilities were greatest for species pairs that shared ecological traits including similar body size, temporal activity pattern and diet. However, co‐occurrence decreased as compared to other species pairs when the pair included a large‐bodied carnivore. Our results suggest that a combination of shared traits and top‐down regulation by large carnivores shape local carnivore communities globally.     

Flexible Regression Model Selection for Survival Probabilities: With Application to AIDS

Summary Clinicians are often interested in the effect of covariates on survival probabilities at prespecified study times. Because different factors can be associated with the risk of short‐ and long‐term failure, a flexible modeling strategy is pursued. Given a set of multiple candidate working models, an objective methodology is proposed that aims to construct consistent and asymptotically normal estimators of regression coefficients and average prediction error for each working model, that are free from the nuisance censoring variable. It requires the conditional distribution of censoring given covariates to be modeled. The model selection strategy uses stepup or stepdown multiple hypothesis testing procedures that control either the proportion of false positives or generalized familywise error rate when comparing models based on estimates of average prediction error. The context can actually be cast as a missing data problem, where augmented inverse probability weighted complete case estimators of regression coefficients and prediction error can be used ( Tsiatis, 2006 , Semiparametric Theory and Missing Data). A simulation study and an interesting analysis of a recent AIDS trial are provided.     

Predicting the Geographic Distribution of a Species from Presence‐Only Data Subject to Detection Errors

Summary Several models have been developed to predict the geographic distribution of a species by combining measurements of covariates of occurrence at locations where the species is known to be present with measurements of the same covariates at other locations where species occurrence status (presence or absence) is unknown. In the absence of species detection errors, spatial point‐process models and binary‐regression models for case‐augmented surveys provide consistent estimators of a species’ geographic distribution without prior knowledge of species prevalence. In addition, these regression models can be modified to produce estimators of species abundance that are asymptotically equivalent to those of the spatial point‐process models. However, if species presence locations are subject to detection errors, neither class of models provides a consistent estimator of covariate effects unless the covariates of species abundance are distinct and independently distributed from the covariates of species detection probability. These analytical results are illustrated using simulation studies of data sets that contain a wide range of presence‐only sample sizes. Analyses of presence‐only data of three avian species observed in a survey of landbirds in western Montana and northern Idaho are compared with site‐occupancy analyses of detections and nondetections of these species.     

On the distributions of bootstrap support and posterior distributions for a star tree

Several authors have recently noted that when data are generated from a star topology, posterior probabilities can often be very large, even with arbitrarily large sequence lengths. This is counter to intuition, which suggests convergence to the limit of equal probability for each topology. Here the limiting distributions of bootstrap support and posterior probabilities are obtained for a four-taxon star tree. Theoretical results are given, providing confirmation that this counterintuitive phenomenon holds for both posterior probabilities and bootstrap support. For large samples the limiting results for posterior probabilities are the same regardless of the prior. With equal-length terminal edges, the limiting distribution is similar but not the same across different choices for the lengths of the edges. In contrast to previous results, the case of unequal lengths of terminal edges is considered. With two long edges, the posterior probability of the tree with long edges together tends to be much larger. Using the neighbor-joining algorithm, with equal edge lengths, the distribution of bootstrap support tends to be qualitatively comparable to posterior probabilities. As with posterior probabilities, when two of the edges are long, bootstrap support for the tree with long branches together tends to be large. The bias is less pronounced, however, as the distribution of bootstrap support gets close to uniform for this tree, whereas posterior probabilities are much more likely to be large. Our findings for maximum likelihood estimation are based entirely on simulation and in contrast suggest that bootstrap support tends to be fairly constant across edge-length choices.     

Bayesian estimators for conditional hazard functions

This article introduces a new Bayesian approach to the analysis of right-censored survival data. The hazard rate of interest is modeled as a product of conditionally independent stochastic processes corresponding to (1) a baseline hazard function and (2) a regression function representing the temporal influence of the covariates. These processes jump at times that form a time-homogeneous Poisson process and have a pairwise dependency structure for adjacent values. The two processes are assumed to be conditionally independent given their jump times. Features of the posterior distribution, such as the mean covariate effects and survival probabilities (conditional on the covariate), are evaluated using the Metropolis-Hastings-Green algorithm. We illustrate our methodology by an application to nasopharynx cancer survival data.     

Estimating Treatment Effects of Longitudinal Designs using Regression Models on Propensity Scores

Summary We derive regression estimators that can compare longitudinal treatments using only the longitudinal propensity scores as regressors. These estimators, which assume knowledge of the variables used in the treatment assignment, are important for reducing the large dimension of covariates for two reasons. First, if the regression models on the longitudinal propensity scores are correct, then our estimators share advantages of correctly specified model‐based estimators, a benefit not shared by estimators based on weights alone. Second, if the models are incorrect, the misspecification can be more easily limited through model checking than with models based on the full covariates. Thus, our estimators can also be better when used in place of the regression on the full covariates. We use our methods to compare longitudinal treatments for type II diabetes mellitus.     

Using mechanistic models to understand synchrony in forest insect populations: the North American gypsy moth as a case study

In many forest insects, subpopulations fluctuate concurrently across large geographical areas, a phenomenon known as population synchrony. Because of the large spatial scales involved, empirical tests to identify the causes of synchrony are often impractical. Simple models are, therefore, a useful aid to understanding, but data often seem to contradict model predictions. For instance, chaotic population dynamics and limited dispersal are not uncommon among synchronous forest defoliators, yet both make it difficult to achieve synchrony in simple models. To test whether this discrepancy can be explained by more realistic models, we introduced dispersal and spatially correlated stochasticity into a mechanistic population model for the North American gypsy moth Lymantria dispar. The resulting model shows both chaotic dynamics and spatial synchrony, suggesting that chaos and synchrony can be reconciled by the incorporation of realistic dynamics and spatial structure. By relating alterations in model structure to changes in synchrony levels, we show that the synchrony is due to a combination of spatial covariance in environmental stochasticity and the origins of chaos in our multispecies model.     

Synchrony in small mammal community dynamics across a forested landscape

Long‐term studies at local scales indicate that fluctuations in abundance among trophically similar species are often temporally synchronized. Complementary studies on synchrony across larger spatial extents are less common, as are studies that investigate the subsequent impacts on community dynamics across the landscape. We investigate the impact of species population fluctuations on concordance in community dynamics for the small mammal fauna of the White Mountain National Forest, USA. Hierarchical open population models, which account for imperfect detection, were used to model abundance of the most common species at 108 sites over a three year period. Most species displayed individualistic responses of abundance to forest type and physiographic characteristics. However, among species, we found marked synchrony in population fluctuations across years, regardless of landscape affinities or trophic level. Across the region, this population synchrony led to high within‐year concordance of community composition and aggregate properties (e.g. richness and diversity) independent of forest type and low among‐year similarity in communities, even for years with similar species richness. Results suggest that extrinsic factors primarily drive abundance fluctuations and subsequently community dynamics, although local community assembly may be modified by species dispersal abilities and biotic interactions. Concordant community dynamics across space and over time may impact the stability of regional food webs and ecosystem functions.     

Does the pattern of population synchrony through space reveal if the Moran effect is acting?

The populations of many species fluctuate in synchrony across large geographical areas. This synchrony is often attributed to the Moran effect, that is, shared environmental fluctuations across the region. In this article, I use a series of simple metapopulation models to show that the degree of synchrony among populations separated by different distances is strongly affected by the particular way that environmental stochasticity is represented in the models. Furthermore, when multiple types of stochasticity are acting simultaneously, the synchronizing effect of any one type is difficult to discern from the resulting pattern of population synchrony. These effects can be exacerbated under certain demographic conditions or if population dynamics are affected by interspecific interactions. In general, it should be extremely difficult to determine if synchrony is caused by the Moran effect using only the synchrony–distance relationship of natural populations.     

Integrating over uncertainty in spatial scale of response within multispecies occupancy models yields more accurate assessments of community composition

Species abundance and community composition are affected not only by the local environment, but also by broader landscape and regional context. Yet, determining the spatial scales at which landscapes affect species remains a persistent challenge, hindering our ability to understand how environmental gradients shape communities. This problem is amplified by rare species and imperfect species detection. Here, we present a Bayesian framework that allows uncertainty surrounding the ‘true’ spatial scale of species’ responses (i.e. changes in presence/absence) to be integrated directly into a community hierarchical model. This scale‐selecting multispecies occupancy model (ssMSOM) estimates the scale of response, and shows high accuracy and correct levels of uncertainty in parameter estimates across a broad range of simulation conditions. An ssMSOM can be run in a matter of minutes, as opposed to the many hours required to run normal multispecies occupancy models at all queried spatial scales, and then conduct model selection – a problem that up to now has prohibited scale of response from being rigorously evaluated in an occupancy framework. Alternatives to the ssMSOM, such as GLM‐based approaches frequently fail to detect the correct spatial scale and magnitude of response, and are often falsely confident by favoring the incorrect parameter estimates, especially as species’ detection probabilities deviate from perfect. We further show how trait information can be leveraged to understand how individual species’ scales of response vary within communities. Integrating spatial scale selection directly into hierarchical community models provides a means of formally testing hypotheses regarding spatial scales of response, and more accurately determining the environmental drivers that shape communities.     

Estimation and identification issues in the promotion time cure model when the same covariates influence long‐ and short‐term survival

The promotion time cure model is a survival model acknowledging that an unidentified proportion of subjects will never experience the event of interest whatever the duration of the follow‐up. We focus our interest on the challenges raised by the strong posterior correlation between some of the regression parameters when the same covariates influence long‐ and short‐term survival. Then, the regression parameters of shared covariates are strongly correlated with, in addition, identification issues when the maximum follow‐up duration is insufficiently long to identify the cured fraction. We investigate how, despite this, plausible values for these parameters can be obtained in a computationally efficient way. The theoretical properties of our strategy will be investigated by simulation and illustrated on clinical data. Practical recommendations will also be made for the analysis of survival data known to include an unidentified cured fraction.     

Bayesian meta-analysis for longitudinal data models using multivariate mixture priors

We propose a class of longitudinal data models with random effects that generalizes currently used models in two important ways. First, the random-effects model is a flexible mixture of multivariate normals, accommodating population heterogeneity, outliers, and nonlinearity in the regression on subject-specific covariates. Second, the model includes a hierarchical extension to allow for meta-analysis over related studies. The random-effects distributions are decomposed into one part that is common across all related studies (common measure), and one part that is specific to each study and that captures the variability intrinsic between patients within the same study. Both the common measure and the study-specific measures are parameterized as mixture-of-normals models. We carry out inference using reversible jump posterior simulation to allow a random number of terms in the mixtures. The sampler takes advantage of the small number of entertained models. The motivating application is the analysis of two studies carried out by the Cancer and Leukemia Group B (CALGB). In both studies, we record for each patient white blood cell counts (WBC) over time to characterize the toxic effects of treatment. The WBCs are modeled through a nonlinear hierarchical model that gathers the information from both studies.     

A multispecies dependent double‐observer model: A new method for estimating multispecies abundance

Conservation of biological communities requires accurate estimates of abundance for multiple species. Recent advances in estimating abundance of multiple species, such as Bayesian multispecies N‐mixture models, account for multiple sources of variation, including detection error. However, false‐positive errors (misidentification or double counts), which are prevalent in multispecies data sets, remain largely unaddressed. The dependent‐double observer (DDO) method is an emerging method that both accounts for detection error and is suggested to reduce the occurrence of false positives because it relies on two observers working collaboratively to identify individuals. To date, the DDO method has not been combined with advantages of multispecies N‐mixture models. Here, we derive an extension of a multispecies N‐mixture model using the DDO survey method to create a multispecies dependent double‐observer abundance model (MDAM). The MDAM uses a hierarchical framework to account for biological and observational processes in a statistically consistent framework while using the accurate observation data from the DDO survey method. We demonstrate that the MDAM accurately estimates abundance of multiple species with simulated and real multispecies data sets. Simulations showed that the model provides both precise and accurate abundance estimates, with average credible interval coverage across 100 repeated simulations of 94.5% for abundance estimates and 92.5% for detection estimates. In addition, 92.2% of abundance estimates had a mean absolute percent error between 0% and 20%, with a mean of 7.7%. We present the MDAM as an important step forward in expanding the applicability of the DDO method to a multispecies setting. Previous implementation of the DDO method suggests the MDAM can be applied to a broad array of biological communities. We suggest that researchers interested in assessing biological communities consider the MDAM as a tool for deriving accurate, multispecies abundance estimates.     

Bayesian Mapping of Lichens Growing on Trees

Suitability of trees as hosts for epiphytic lichens are studied in a forest stand of size 25 ha. Suitability is measured as occupation probabilites which are modelled using hierarchical Bayesian approach. These probabilities are useful for an ecologist. They give smoothed spatial distribution map of suitability for each of the species and can be used in detecting high‐ and low‐probability areas. In addition, suitability is explained by tree‐level covariates. Spatial dependence, which is due to unobserved spatially structured covariates, is modelled through an unobserved Markov random field. Markov chain Monte Carlo method has been applied in Bayesian computation. The extensive spatial data consist of the occurrences of eight lichen species and one bryophyte on all of the 1253 potential host trees. In addition, coordinates of the trees and several tree characteristics have been recorded. The data have been analysed for four most abundant species: Lobaria pulmonaria, Nephroma bellum, Nephroma parile and Peltigera praetextata. The tree level parameters, subject to estimation, consist of the occurrence probabilities for each tree and for each lichen species. Model validation is discussed in detail and, in addition to Bayesian validation tools, the autologistic model and case‐control design based on logistic regression have been suggested for validation of covariate effects. As a result we present suitability maps for the four lichen species. We observed, that among the observed tree covariates, the diameter at breast height (DBH) correlates with lichen occurrence. Our modelling approach has close connections to disease mapping in spatial epidemiology.     

Relative Selection Strength: Quantifying effect size in habitat‐ and step‐selection inference

Habitat‐selection analysis lacks an appropriate measure of the ecological significance of the statistical estimates—a practical interpretation of the magnitude of the selection coefficients. There is a need for a standard approach that allows relating the strength of selection to a change in habitat conditions across space, a quantification of the estimated effect size that can be compared both within and across studies. We offer a solution, based on the epidemiological risk ratio, which we term the relative selection strength (RSS ). For a “used‐available” design with an exponential selection function, the RSS provides an appropriate interpretation of the magnitude of the estimated selection coefficients, conditional on all other covariates being fixed. This is similar to the interpretation of the regression coefficients in any multivariable regression analysis. Although technically correct, the conditional interpretation may be inappropriate when attempting to predict habitat use across a given landscape. Hence, we also provide a simple graphical tool that communicates both the conditional and average effect of the change in one covariate. The average‐effect plot answers the question: What is the average change in the space use probability as we change the covariate of interest, while averaging over possible values of other covariates? We illustrate an application of the average‐effect plot for the average effect of distance to road on space use for elk (Cervus elaphus ) during the hunting season. We provide a list of potentially useful RSS expressions and discuss the utility of the RSS in the context of common ecological applications.     

Estimating species – area relationships by modeling abundance and frequency subject to incomplete sampling

Models and data used to describe species–area relationships confound sampling with ecological process as they fail to acknowledge that estimates of species richness arise due to sampling. This compromises our ability to make ecological inferences from and about species–area relationships. We develop and illustrate hierarchical community models of abundance and frequency to estimate species richness. The models we propose separate sampling from ecological processes by explicitly accounting for the fact that sampled patches are seldom completely covered by sampling plots and that individuals present in the sampling plots are imperfectly detected. We propose a multispecies abundance model in which community assembly is treated as the summation of an ensemble of species‐level Poisson processes and estimate patch‐level species richness as a derived parameter. We use sampling process models appropriate for specific survey methods. We propose a multispecies frequency model that treats the number of plots in which a species occurs as a binomial process. We illustrate these models using data collected in surveys of early‐successional bird species and plants in young forest plantation patches. Results indicate that only mature forest plant species deviated from the constant density hypothesis, but the null model suggested that the deviations were too small to alter the form of species–area relationships. Nevertheless, results from simulations clearly show that the aggregate pattern of individual species density–area relationships and occurrence probability–area relationships can alter the form of species–area relationships. The plant community model estimated that only half of the species present in the regional species pool were encountered during the survey. The modeling framework we propose explicitly accounts for sampling processes so that ecological processes can be examined free of sampling artefacts. Our modeling approach is extensible and could be applied to a variety of study designs and allows the inclusion of additional environmental covariates.