Bayesian Inference from Count Data using Discrete Uniform Priors.
dupiR: an R package for Bayesian inference using discrete uniform priors
This R package implements a Bayesian approach to infer population sizes from count data. The package takes a set of sample counts obtained by sampling fractions of a finite volume containing an homogeneously dispersed population of identical objects and returns the posterior probability distribution of the population size. The algorithm makes use of a binomial likelihood and non-conjugate, discrete uniform priors. dupiR can be applied to both sampling with or without replacement.
Further details on the statistical framework can be found in:
- Comoglio F, Fracchia L, Rinaldi M (2013) Bayesian Inference from Count Data Using Discrete Uniform Priors. PLoS ONE 8(10): e74388
Please cite this article if you are using dupiR for your research.
Installation
You can install the latest package release from CRAN:
install.packages("dupiR")
or the development version from GitHub:
# install.packages("devtools")
devtools::install_github("FedericoComoglio/dupiR")