Learn R Programming

uni.survival.tree (version 1.5)

A Survival Tree Based on Stabilized Score Tests for High-dimensional Covariates

Description

A classification (decision) tree is constructed from survival data with high-dimensional covariates. The method is a robust version of the logrank tree, where the variance is stabilized. The main function "uni.tree" returns a classification tree for a given survival dataset. The inner nodes (splitting criterion) are selected by minimizing the P-value of the two-sample the score tests. The decision of declaring terminal nodes (stopping criterion) is the P-value threshold given by an argument (specified by user). This tree construction algorithm is proposed by Emura et al. (2021, in review).

Copy Link

Version

Install

install.packages('uni.survival.tree')

Monthly Downloads

125

Version

1.5

License

GPL-3

Maintainer

Takeshi Emura

Last Published

March 22nd, 2021

Functions in uni.survival.tree (1.5)

feature.selected

The names of features that are selected in a tree
risk.classification

The risk ranks of the samples predicted by a tree
uni.logrank

Univariate binary splits by the logrank test
uni.tree

A survival tree based on stabilized score tests
X.pathway_discrete.balanced

Generate a matrix of gene expressions (discrete version of X.pathway() against to Emura (2012)) in the presence of gene pathways
X.pathway_discrete.imbalanced

Generate a matrix of unbalance gene expressions (discrete version of X.pathway() against to Emura (2012)) in the presence of gene pathways
KM.split

Kaplan-Meier estimator of binary splitting