"VariableSelection” package enables users to identify the set of predictors of a binary outcome. The package is a simple tool to help researchers put aside any doubts they have regarding the complexity of modern methods or statistical software programming; using a single command, the researcher can implement various approaches of variable selection on his/er own dataset. Such methods include filters and wrappers containing more than 20 specific approaches. Numerical and graphical outputs are easily obtained as well.
To install and load the package from github, type:
install.packages("devtools")
devtools::install_github("faridehbagherzadeh/VariableSelection")
library(VariableSelection)
The file 'VariableSelection.pdf' shows how to use the package. The functions of the package (VariableSelection) along with their parameters are described in this manual.
This package is released in association with the following paper:
Farideh Bagherzadeh Khiabani, Azra Ramezankhani, Fereidoun Azizi, Farzad Hadaegh, Ewout W Steyerberg, Davood Khalili: A tutorial on variable selection for clinical prediction models: Feature selection methods in data-mining could improve the results. Journal of clinical epidemiology 10/2015; DOI:10.1016/j.jclinepi.2015.10.002
A site for the package has been developed: http://faridehbagherzadeh.github.io/VariableSelection
The codes are not yet perfect. We are still working on the debugging and generalization of the package to submit it to CRAN. Any recommendation is welcomed.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.