Accurate, Adaptable, and Accessible Error Metrics for Predictive Models

Supplies tools for tabulating and analyzing the results of predictive models. The methods employed are applicable to virtually any predictive model and make comparisons between different methodologies straightforward.


News

2015-08-15 version 1.0.0

  • Fixed fatal error with explanatory variables that are factors with more than two categories
  • Drop unused levels for factor explanatory variables
  • Added the optional slope.sample parameter to a3.base controlling the sample size for average slope estimation
  • Formatted slope values to remove gratuitous digits
  • Added citation to JSS A3 article
  • Fixed a few R CMD check issues

2012-03-24 version 0.9.2

  • Clarifications and documentation improvements
  • Improved formatting of LaTeX xtable output
  • Fixed fatal error with models containing only one independent variable
  • Improved handling of custom model.args
  • Fixed issue with sign display in output table for full models worse than the null model
  • Changed default data generator to handle constant terms using a normal distribution data generator instead of a resampling based one
  • Added dependency for R 2.15.0 or higher

2012-02-06 version 0.9.1

  • Added \donttest{} to some of the examples to reduce CMD CHECK computation time

2012-02-01 version 0.9.0

  • Initial Release

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("A3")

1.0.0 by Scott Fortmann-Roe, 4 years ago


Browse source code at https://github.com/cran/A3


Authors: Scott Fortmann-Roe


Documentation:   PDF Manual  


GPL (>= 2) license


Depends on xtable, pbapply

Suggests randomForest, e1071


See at CRAN