[R-pkgs] randomSurvivalForest 3.6.0 now available on CRAN

Udaya B. Kogalur ubk2101 at columbia.edu
Mon Dec 21 19:15:36 CET 2009

Please find release 3.6.0 of the package "randomSurvivalForest" now
available for download on CRAN.


RELEASE 3.6.0 represents the last and final major upgrade
of this product.  Current and future functionality will migrate to the
new CRAN package, Random Forests for Survival, Regression, and
Classification, that will be released in the coming months.

Key changes to the current release are as follows:

o The ability to fully analyze competing risk data including ensemble
 estimation, error rates, and VIMP by event type.  Can also predict
 on test data.  Missing data imputation is also available. See rsf()
 and competing.risk() for details.

o Automatic variable selection using minimal depth theory implemented
 in the new function varSel().  Also see the core function

o Pairwise interactions between variables using minimal depth theory.
 See find.interaction() for more details.

o The ability to analyze mean minimal depth information by individual
 (for variable selection at the individual level). See the
 documentation for rsf() for more information.

o Impute only mode for extremely fast imputation of data.  See the
 documentation for impute.rsf() fro more details.

o The ability to export forests to a Java (JUNG) based plug-in.  This
 allows one to visualize individual trees in the forest. See the
 documentation for rsf2rfz() for more information.

o Modification to random splitting to grow deeper trees.

o Fix of memory leak in INTERACTION mode.  Thanks to Xi Chen for
 finding this feature.  Other miscellaneous bug fixes.


udaya at kogalur-shear.com

Udaya B. Kogalur, Ph.D.
Adjunct Staff, Dept of Quantitative Health Sciences, Cleveland Clinic Foundation
President, Kogalur Shear Corporation
5425 Nestleway Drive, Suite L1
Clemmons, NC 27012

More information about the R-packages mailing list