Fit the Gambin Model to Species Abundance Distributions

Fits unimodal and multimodal gambin distributions to species-abundance distributions from ecological data, as in in Matthews et al. (2014) . 'gambin' is short for 'gamma-binomial'. The main function is fit_abundances(), which estimates the 'alpha' parameter(s) of the gambin distribution using maximum likelihood. Functions are also provided to generate the gambin distribution and for calculating likelihood statistics.

The gambin R package

This package fits the gambin distribution to species-abundance distributions from ecological data. 'gambin' is short for 'gamma-binomial'. The main functions are fit_abundances, which estimates the alpha parameter of the gambin distribution using maximum likelihood, and mult_abundances which estimates alpha for multiple sites / samples after standardising for the number of individuals. Recent functions are also provided to generate the gambin distribution and for calculating likelihood statistics. The package now provides functionality to fit multimodal gambin distributions.

The package is currently on CRAN and can be installed via

install.packages("gambin")

Alternatively, you can install the developmental version via

devtools::install_github("txm676/gambin")

News

Version 2.4.1

Vignette edit to pass CRAN check

Version 2.4.0

Bug fix: confidence intervals for alpha
New tests included
Adding a new 'deconstruct_modes' function to enable more in depth analysis of a multimodal gambin model fit
Confidence intervals for multi-component gambin model parameters

Version 2.3.0

Adding a new 'mult_abundances' function to fit gambin to muliple sites and calculate standardised alpha

Version 2.2.0

Adding a new dataset (Brazilian flies)

Version 2.1.0

Adding support for mixture models

Version 2.0.0

Code refactored
Create r/q/p/d gambin functions
Number of considered free parameters increased from 1 to 2
Created an initial vignette.
Created an initial test suite
Hooked up to travis and codecov
Created d/r/p/q functions
Minor optimisation on fitGam
Move plot to barplot, lines, points. You can now pass standard plotting arguments and everything will work as expected.
Created README.Rmd to generate README.md
Created NEWS.md
Updated DESCRIPTION with URL