A backward selection procedure called delete or merge regressors (DMR) combines deleting continuous variables with merging levels of factors. The method assumes greedy search among linear models with set of constraints of two types: either a parameter for a continuous variable is set to zero or parameters corresponding to two levels of a factor are compared. DMR is a stepwise regression procedure, where in each step a new constraint is added according to ranking of the hypotheses based on squared tstatistics. As a result a nested family of linear models is obtained and the final decision is made according to minimization of the generalized information criterion (GIC, default BIC). The main function of the package is DMR, which is based on hierarchical clustering. Moreover, other functions for extensions of DMR method are given, such as stepDMR which is based on recalculation of tstatistics in each step and function DMR4glm for generalized linear models.
Browse man pages Browse package API and functions Browse package files
Author  Aleksandra Maj, Agnieszka Prochenka, Piotr Pokarowski 
Date of publication  20130221 13:19:28 
Maintainer  Aleksandra Maj <aleksandra.lucja.maj@gmail.com> 
License  GPL2 
Version  2.0 
Package repository  View on CRAN 
Installation  Install the latest version of this package by entering the following in R:

Package overview 
Functions  

DMR  Man page Source code 
DMRpackage  Man page 
DMR4glm  Man page Source code 
cuth  Source code 
cuth4glm  Source code 
hip  Source code 
part2hi  Source code 
plot_bf  Man page Source code 
roc  Man page Source code 
stepDMR  Man page Source code 
t_stats  Source code 
Files  

MD5
 
R
 
R/plot_bf.r  
R/t_stats.r  
R/stepDMR.r  
R/roc.r  
R/part2hi.r  
R/hip.r  
R/DMR4glm.r  
R/DMR.r  
R/cuth4glm.r  
R/cuth.r  
NAMESPACE
 
man
 
man/plot_bf.Rd  
man/stepDMR.Rd  
man/roc.Rd  
man/DMR4glm.Rd  
man/DMR.Rd  
man/DMRpackage.Rd  
DESCRIPTION

Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.