The goal of bayesplay is to provide an interface for calculating Bayes factors for simple models. It does this in a way that makes the calculations more transparent and it is therefore useful as a teaching tools.
bayesplay is now on CRAN. You can install it with:
install.packages("bayesplay")
Or if you want to live on the edge, you can install the development version from GitHub with:
# install.packages("devtools")
devtools::install_github("bayesplay/bayesplay")
The bayesplay
package comes with three basic functions for computing
Bayes factors.
The likelihood()
function for specifying likelihoods
The prior()
function for specifying priors
And the integral()
function
Currently the following distributions are supported for likelihoods and priors
Normal distribution (normal
)
Uniform distribution (uniform
)
Scaled and shifted t distribution (student_t
)
Cauchy distributions (cauchy
)
Beta distribution (beta
)
Normal distribution (normal
)
Scaled and shifted t distribution (student_t
)
Binomial distribution (binomial
)
Various noncentral t distributions, including:
Noncentral t distribution (noncentral_t
)
Noncentral t distribution scaled for a paired samples/one
sample Cohen’s d (noncentral_d
)
Noncentral t distribution scaled for an independent samples
Cohen’s d (noncentral_d2
)
For worked examples of the basic usage see basic usage. Or for basic plot functionality see basic plotting
Breaking changes for < v0.9.0
distribution
parameter for specifying likelihoods and priors has been renamedfamily
noncentral_d
andnoncentral_d2
are now parametrised in terms of sample size rather than df
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.