Bayesian

Bayesian inference of bipartite networks structure

Inferring the structure of bipartite (e.g. pollination, frugivory, or herbivory) networks from field (observational) data is a challenging task. Interaction data are hard to collect and require typically large sampling efforts, particularly to characterize infrequent interactions.

Lasting effects of avian-frugivore interactions on seed dispersal and seedling establishment

The consequences of plant–animal interactions often transcend the mere encounter stage, as those encounters are followed by a chain of subsequent stages on the plant’s reproductive cycle that ultimately determine fitness. Yet, the dissemination and …

Reciprocity and interaction effectiveness in generalised mutualisms among free-living species

Mutualistic interactions among free-living species generally involve weak links and highly asymmetric dependence among partners, yet our understanding of factors beyond their emergence is still limited. Using individual-based interactions of a …

Limits to reproduction and seed size-number trade-offs that shape forest dominance and future recovery

The relationships that control seed production in trees are fundamental to understanding the evolution of forest species and their capacity to recover from increasing losses to drought, fire, and harvest. A synthesis of fecundity data from 714 …

Globally, tree fecundity exceeds productivity gradients

Lack of tree fecundity data across climatic gradients precludes the analysis of how seed supply contributes to global variation in forest regeneration and biotic interactions responsible for biodiversity. A global synthesis of raw seedproduction data …

DHARMa.helpers: helper functions to check Bayesian brms models with DHARMa

Using DHARMa to check Bayesian models fitted with brms

UPDATE 26 October 2022: There is now a DHARMa.helpers package that facilitates checking Bayesian brms models with DHARMa. Check it out! The R package DHARMa is incredibly useful to check many different kinds of statistical models.

Long-term hurricane damage effects on tropical forest tree growth and mortality

Hurricane winds can have large impacts on forest structure and dynamics. To date, most evaluations of hurricane impacts have focused on short-term responses after a hurricane, often lacked pre-hurricane measurements, and missed responses occurring …

Model selection in practice (or 'Which variables should I keep in my model?')

Slides discussing variable selection, information criteria (AIC, BIC, DIC), and other statistical modelling issues, with a focus on modelling ecological data.

Model selection and balanced complexity: AIC, BIC, DIC and beyond

Some notes on statistical model selection and comparison, balanced model complexity and predictive accuracy. An overview of different information criteria (AIC, BIC, DIC, WAIC) and cross validation. Mostly taken from Gelman et al.'s recent paper: …