Random survival forests for high-dimensional data

Hemant Ishwaran, Udaya B. Kogalur, Xi Chen, Andy J. Minn

Code and Data Abstract

Minimal depth is a dimensionless order statistic that measures the predictiveness of a variable in a survival tree. It can be used to select variables in high-dimensional problems using Random Survival Forests (RSF), a new extension of Breiman's Random Forests (RF) to survival settings. We review this methodology and demonstrate its use in high-dimensional survival problems using a public domain R-language package randomSurvivalForest. We discuss effective ways to regularize forests and discuss how to properly tune the RF parameters ‘nodesize’ and ‘mtry’. We also introduce new graphical ways of using minimal depth for exploring variable relationships.

Article

Hemant Ishwaran, Udaya B. Kogalur, Xi Chen, Andy J. Minn, et al. 2011. "Random survival forests for high-dimensional data." Statistical Analysis and Data Mining. 4 (1) 115–132.    doi:10.1002/sam.10103. Retrieved 09/15/2019 from researchcompendia.org/compendia/2014.462/

Compendium Type: Journal or Magazine Articles
Primary Research Field: Computer and Information Sciences
Secondary Research Field: Mathematics
Content License: Public Domain Mark
Code License: MIT License

Page Owner

jenn.seiler@gmail.com

created 03/07/2014

modified 03/07/2014

blog comments powered by Disqus