selectCox: Backward variable selection in the Cox regression model

In riskRegression: Risk Regression Models and Prediction Scores for Survival Analysis with Competing Risks

Backward variable selection in the Cox regression model

Description

This is a wrapper function which first selects variables in the Cox regression model using fastbw from the rms package and then returns a fitted Cox regression model with the selected variables.

Usage

selectCox(formula, data, rule = "aic")

Arguments

formula	A formula object with a Surv object on the left-hand side and all the variables on the right-hand side.
data	Name of an data frame containing all needed variables.
rule	The method for selecting variables. See fastbw for details.

Details

This function first calls cph then fastbw and finally cph again.

References

Ulla B. Mogensen, Hemant Ishwaran, Thomas A. Gerds (2012). Evaluating Random Forests for Survival Analysis Using Prediction Error Curves. Journal of Statistical Software, 50(11), 1-23. URL http://www.jstatsoft.org/v50/i11/.

Examples

library(survival)
set.seed(74)
d <- sampleData(89,outcome="survival")
f <- selectCox(Surv(time,event)~X1+X2+X3+X4+X6+X7+X8+X9, data=d)

riskRegression documentation built on May 29, 2024, 10:59 a.m.