Main Article Content
The observation that species may be positively or negatively associated with each other is at least as old as the debate surrounding the nature of community structure which began in the early 1900's with Gleason and Clements. Since then investigating species co-occurrence patterns has taken a central role in understanding the causes and consequences of evolution, history, coexistence mechanisms, competition, and environment for community structure and assembly. This is because co-occurrence among species is a measurable metric in community datasets that, in the context of phylogeny, geography, traits, and environment, can sometimes indicate the degree of competition, displacement, and phylogenetic repulsion as weighed against biotic and environmental effects promoting correlated species distributions. Historically, a multitude of different co-occurrence metrics have been developed and most have depended on data randomization procedures to produce null distributions for significance testing. Here we improve upon and present an R implementation of a recently published model that is metric-free, distribution-free, and randomization-free. The R package, cooccur, is highly accessible, easily integrates into common analyses, and handles large datasets with high performance. In the article we develop the package's functionality and demonstrate aspects of co-occurrence analysis using three sample datasets.