So Many Variables: Joint Modeling in Community Ecology.

Published on Dec 1, 2015in Trends in Ecology and Evolution15.236
· DOI :10.1016/j.tree.2015.09.007
David I. Warton35
Estimated H-index: 35
(UNSW: University of New South Wales),
F. Guillaume Blanchet15
Estimated H-index: 15
(McMaster University)
+ 4 AuthorsFrancis K. C. Hui14
Estimated H-index: 14
(ANU: Australian National University)
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.
  • References (88)
  • Citations (208)
📖 Papers frequently viewed together
193 Citations
126 Citations
71 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
type="main" xml:id="stan12066-abs-0001"> Typical data that arise from surveys, experiments, and observational studies include continuous and discrete variables. In this article, we study the interdependence among a mixed (continuous, count, ordered categorical, and binary) set of variables via graphical models. We propose an l 1 -penalized extended rank likelihood with an ascent Monte Carlo expectation maximization approach for the copula Gaussian graphical models and establish near conditional ...
9 CitationsSource
#1Douglas M. BatesH-Index: 32
#2Martin MächlerH-Index: 16
Last. Steve WalkerH-Index: 2
view all 4 authors...
Maximum likelihood or restricted maximum likelihood (REML) estimates of the parameters in linear mixed-effects models can be determined using the lmer function in the lme4 package for R. As for most model-fitting functions in R, the model is described in an lmer call by a formula, in this case including both fixed- and random-effects terms. The formula and data together determine a numerical representation of the model from which the profiled deviance or the profiled REML criterion can be evalua...
14.9k CitationsSource
#1Andrew D. Letten (UNSW: University of New South Wales)H-Index: 10
#2David A. Keith (UNSW: University of New South Wales)H-Index: 47
Last. Francis K. C. Hui (UNSW: University of New South Wales)H-Index: 14
view all 4 authors...
Summary Theory suggests spatial heterogeneity can facilitate species co-occurrence at fine scales, but environmental data are rarely collected at sufficiently high resolution to test this empirically. Whilst there is emerging evidence that subtle variation in soil hydrology represents a fundamental fine-scale niche axis within plant communities, this is largely derived from studies of soil hydrology in isolation from other environmental factors. We assessed the comparative importance of fine-sca...
22 CitationsSource
#1Pedro J. Leitão (Humboldt University of Berlin)H-Index: 18
#2Marcel Schwieder (Humboldt University of Berlin)H-Index: 7
Last. Patrick Hostert (Humboldt University of Berlin)H-Index: 46
view all 10 authors...
Summary 1. Spatial patterns of community composition turnover (beta diversity) may be mapped through generalised dissimilarity modelling (GDM). While remote sensing data are adequate to describe these patterns, the often high-dimensional nature of these data poses some analytical challenges, potentially resulting in loss of generality. This may hinder the use of such data for mapping and monitoring beta-diversity patterns. 2. This study presents Sparse Generalised Dissimilarity Modelling (SGDM),...
11 CitationsSource
#1Jonathan Belmaker (TAU: Tel Aviv University)H-Index: 20
#2Walter Jetz (Yale University)H-Index: 64
Regions worldwide differ markedly in species richness. Here, for birds and mammals worldwide, we directly compare four sets of hypotheses regarding geographical richness gradients: (1) evolutionary, emphasising heterogeneity in diversification rates, (2) historical, related to differences in region ages and sizes, (3) energetic, associated with variation in productive or ambient energy and (4) ecological, reflecting differences in ecological niche diversity. Among highly independent regions, or ...
67 CitationsSource
#1Ignacio Morales-Castilla (McGill University)H-Index: 12
#2Miguel G. Matias (University of Évora)H-Index: 10
Last. Miguel B. Araújo (University of Évora)H-Index: 78
view all 4 authors...
Inferring biotic interactions from functional, phylogenetic and geographical proxies remains one great challenge in ecology. We propose a conceptual framework to infer the backbone of biotic interaction networks within regional species pools. First, interacting groups are identified to order links and remove forbidden interactions between species. Second, additional links are removed by examination of the geographical context in which species co-occur. Third, hypotheses are proposed to establish...
124 CitationsSource
#1James T. Thorson (NMFS: National Marine Fisheries Service)H-Index: 25
#2Mark D. Scheuerell (NMFS: National Marine Fisheries Service)H-Index: 30
Last. Kasper Kristensen (DTU: Technical University of Denmark)H-Index: 14
view all 6 authors...
Summary Predicting and explaining the distribution and density of species is one of the oldest concerns in ecology. Species distributions can be estimated using geostatistical methods, which estimate a latent spatial variable explaining observed variation in densities, but geostatistical methods may be imprecise for species with low densities or few observations. Additionally, simple geostatistical methods fail to account for correlations in distribution among species and generally estimate such...
53 CitationsSource
#1Eduard Szöcs (University of Koblenz and Landau)H-Index: 9
#2Ralf B. Schäfer (University of Koblenz and Landau)H-Index: 31
Ecotoxicologists often encounter count and proportion data that are rarely normally distributed. To meet the assumptions of the linear model, such data are usually transformed or non-parametric methods are used if the transformed data still violate the assumptions. Generalized linear models (GLMs) allow to directly model such data, without the need for transformation. Here, we compare the performance of two parametric methods, i.e., (1) the linear model (assuming normality of transformed data), ...
17 CitationsSource
#1Tim S. Doherty (ECU: Edith Cowan University)H-Index: 12
#2Robert A. Davis (ECU: Edith Cowan University)H-Index: 10
Last. Sue Robinson (Hobart Corporation)H-Index: 3
view all 10 authors...
Aim Reducing the impacts of feral cats (Felis catus) is a priority for conservation managers across the globe, and success in achieving this aim requires a detailed understanding of the species’ ecology across a broad spectrum of climatic and environmental conditions. We reviewed the diet of the feral cat across Australia and on Australian territorial islands, seeking to identify biogeographical patterns in dietary composition and diversity, and use the results to consider how feral cats may bes...
77 CitationsSource
#1David I. Warton (UNSW: University of New South Wales)H-Index: 35
#2Scott D. Foster (CSIRO: Commonwealth Scientific and Industrial Research Organisation)H-Index: 15
Last. Piers K. Dunstan (CSIRO: Commonwealth Scientific and Industrial Research Organisation)H-Index: 24
view all 5 authors...
In this paper, a case is made for the use of model-based approaches for the analysis of community data. This involves the direct specification of a statistical model for the observed multivariate data. Recent advances in statistical modelling mean that it is now possible to build models that are appropriate for the data which address key ecological questions in a statistically coherent manner. Key advantages of this approach include interpretability, flexibility, and efficiency, which we explain...
68 CitationsSource
Cited By208
#1Mervi Laaksonen (UH: University of Helsinki)H-Index: 2
#2Pekka Punttila (SYKE: Finnish Environment Institute)H-Index: 26
Last. Otso Ovaskainen (UH: University of Helsinki)H-Index: 50
view all 4 authors...
Abstract Boreal forests have been intensively managed, influencing the spatiotemporal occurrence of dead wood, and leading to changes in saproxylic species assemblages. Some particular traits, such as habitat specialization, can be expected to make species sensitive to alterations in the amount, dynamics and heterogeneity of dead-wood habitats. We compared the saproxylic beetle assemblages of 320 dead standing Scots pines within 52 pine forest stands in three regions in Finland and Russia with c...
#1Ji Yoon Kim (Toho University)H-Index: 10
#2Jun Nishihiro (Toho University)H-Index: 13
Abstract Aquatic plants are essential components in the regulation of microhabitat complexity and physico-chemical parameters in lake ecosystems. Increased eutrophication, land use change, modification of hydrological regimes, and expansion of invasive species are expected to impact aquatic plant community composition; however, historical pathways and response patterns are not well understood at the national scale. We analyzed temporal changes in aquatic plant communities in Japan from the early...
#1Andrés Muñoz-Sáez (University of Chile)H-Index: 1
#2Emily Heaton (University of California, Berkeley)H-Index: 2
Last. Adina M. Merenlender (University of California, Berkeley)H-Index: 28
view all 4 authors...
Abstract Agricultural expansion changes wildlife communities. Some species adapt to working lands, increasing their relative abundance in these modified landscapes, and this may result in spillover effects for communities in adjacent wildlands. These effects remain largely undocumented, even though they can affect biodiversity conservation. We conducted bird surveys at 130 Mediterranean-climate oak woodland locations that exist across a gradient of nearby vineyard development. We used zero infla...
#1Jenna Purhonen (University of Jyväskylä)H-Index: 3
#2Otso Ovaskainen (UH: University of Helsinki)H-Index: 50
Last. Nerea Abrego (UH: University of Helsinki)H-Index: 12
view all 8 authors...
Abstract Tree species is one of the most important determinants of wood-inhabiting fungal community composition, yet its relationship with fungal reproductive and dispersal traits remains poorly understood. We studied fungal communities (total of 657 species) inhabiting broadleaved and coniferous dead wood (total of 192 logs) in 12 semi-natural boreal forests. We utilized a trait-based hierarchical joint species distribution model to examine how the relationship between dead wood quality and spe...
Abstract The European eel is critically endangered and European member states are required to undertake measures to ensure the recovery of eel stocks. The otter is also a protected species under international legislation. As a predator of the eel the otter is often caught in fyke nets located close to shore and in shallow water and otter guards can be used to reduce this unwanted by-catch. This study was undertaken to investigate the effect of otter guards in fyke nets on 1) eel catch and 2) eel...
#1Otso Ovaskainen (UH: University of Helsinki)H-Index: 50
#2Nerea Abrego (UH: University of Helsinki)H-Index: 12
#1Jamie M. KassH-Index: 5
Last. Fumito KoikeH-Index: 13
view all 4 authors...
#1Limoilou-A. Renaud (Université de Sherbrooke)
#2François Rousseu (Université de Sherbrooke)H-Index: 1
Last. Fanie Pelletier (Université de Sherbrooke)H-Index: 31
view all 6 authors...
Understanding how spring phenology influences early life can provide important insights into drivers of future development and survival. We combined unique, long-term data from a bighorn sheep population and satellite-derived phenology indices to quantify the relative importance of maternal and environmental influences on milk composition and lamb overwinter survival. Based on 216 milk samples from 34 females monitored over 6 years, we found that longer snow-free and vegetation growing seasons i...