Model‐based hypervolumes for complex ecological data

Abstract

Developing a holistic understanding of the ecosystem impacts of global change requires methods that can quantify the interactions among multiple response variables. One approach is to generate high dimensional spaces, or hypervolumes, to answer ecological questions in a multivariate context. A range of statistical methods has been applied to construct hypervolumes but have not yet been applied in the context of ecological data sets with spatial or temporal structure, for example, where the data are nested or demonstrate temporal autocorrelation. We outline an approach to account for data structure in quantifying hypervolumes based on the multivariate normal distribution by including random effects. Using simulated data, we show that failing to account for structure in data can lead to biased estimates of hypervolume properties in certain contexts. We then illustrate the utility of these “model‐based hypervolumes” in providing new insights into a case study of afforestation effects on ecosystem properties where the data has a nested structure. We demonstrate that the model‐based generalization allows hypervolumes to be applied to a wide range of ecological data sets and questions.

Soil health cluster analysis based on national monitoring of soil indicators

“…The pH trigger values for supporting metal retention and microbial function are actually contradictory to those suggested for supporting acid grassland and heathland habitats (<5 and >5, respectively), and recent results indicate microbial function may decrease below pH 5.5 rather than 5, exacerbating this difference (Jones, Cooledge, Hoyle, Griffiths, & Murphy, 2019). This shows the difficulties in designating appropriate boundaries when multiple functions and services are involved, especially when the different functions show differing responsiveness to change (Bhogal et al, 2008; Bünemann et al, 2018; Jarvis et al, 2019).…”

Community assembly during vegetation succession after metal mining is driven by multiple processes with temporal variation

“…The FTS for the comprehensive leaf traits was used to represent establishment (Benavides et al, 2019 ). The n‐dimensional hypervolume proposed by Hutchinson is used widely in ecology (Cooke et al, 2019 ; Jarvis et al, 2019 ; Pigliucci, 2007 ), particularly in FTS construction (Lamanna et al, 2014 ; Loranger, Violle, et al, 2016 ) and is calculated from data in n‐dimensional space. The geometric parameters of the hypervolume may be expressed by statistics (Blonder et al, 2014 ) representing the variation (volume), comprehensive trait value (centroid) (Benavides et al, 2019 ), and similarity (overlap, minimum and maximum distances) between two functional trait datasets (Mammola, 2019 ).…”

A Landscape Epidemiological Approach for Predicting Chronic Wasting Disease: A Case Study in Virginia, US

“…Based on the long-term nature of our remote sensing data (i.e., 176 months of EVI data), our PCA generated 176 PCs, which were reduced to the first four statistically significant PCsexplaining 67% of total variance-via the broken-stick method (53). Significance was determined by whether the observed eigenvalues exceed those generated from null theoretical components (53)(54)(55). The first four PCs were used in our modeling as rasterized dimensions in environmental space.…”