The goal of alphaN is to help the user set their significance level as a
function of the sample size. The function alphaN allows users to set
the significance level as function of the sample size based on the
evidence and the prior features they desire. The function JABt and
JABp converts test statistics and JAB_plot plots the Bayes factor as a function
of the alphaN_plot plots the alpha level as a function
of sample size for a given Bayes factor.
Calculations are based on Wulff & Taylor (2024). If you enjoy the package, please consider citing the paper.
If you’re not an R user, you may also be interested in the associated Shiny app.
To install the latest release version from CRAN use
install.packages("alphaN")You can install the development version of alphaN from GitHub with:
# install.packages("devtools")
devtools::install_github("jespernwulff/alphaN")Here is an example: We are planning to run a linear regression model
with 1000 observations. We thus set n = 1000. The default BF is 1
meaning that we want to avoid Lindley’s paradox, i.e. we just want the
null and the alternative to be at least equally likely when we reject
the null.
library(alphaN)
alpha <- alphaN(n = 1000, BF = 1)
alpha
#> [1] 0.008582267Therefore, to obtain evidence of at least 1, we should set our alpha to 0.0086.