BayesGLM
is intended to provide a unified framework for fitting univariate generalized linear models using data augmentation techniques that allow for convenient Gibb's sampling. Despite the name, BayesGLM
includes functionality that goes beyond traditional generalized linear model theory. Some features of BayesGLM
that are novel include
1) BayesGLM
is built around the tidy modeling framework allowing for compatibility with other tidyverse packages and ensuring a consistent modeling interface.
2) BayesGLM
can accomodate non-standard error distributions, such as the skew-normal distribution.
3) BayesGLM
allows for modeling quantiles instead of means.
NOTE: BayesGLM
is under development and the features described above are aspirational at the moment.
devtools::install_github("carter-allen/BayesGLM")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.