comp.cutpoints: Selection of optimal number of cut points

Description

Compares two objects of class "catpredi".

Usage

comp.cutpoints(obj1, obj2, V = 100)

Arguments

obj1

an object inheriting from class "catpredi" for k number of cut points

obj2

an object inheriting from class "catpredi" for k+1 number of cut points

Number of bootstrap resamples. By default V=100

Value

This function returns an object of class "comp.cutpoints" with the following components:

AUC.cor.diff

the difference of the bias corrected AUCs for the two categorical variables.

icb.auc.diff

bootstrap based confidence interval for the bias corrected AUC difference.

References

I Barrio, I Arostegui, M.X Rodriguez-Alvarez and J.M Quintana (2015). A new approach to categorising continuous variables in prediction models: proposal and validation. Statistical Methods in Medical Research (in press).

Examples

Run this code

# NOT RUN {
library(CatPredi)
set.seed(127)
#Simulate data
  n = 100
  #Predictor variable
  xh <- rnorm(n, mean = 0, sd = 1)
  xd <- rnorm(n, mean = 1.5, sd = 1)
  x <- c(xh, xd)
  #Response
  y <- c(rep(0,n), rep(1,n))
  # Data frame
  df <- data.frame(y = y, x = x)
# }
# NOT RUN {
  # Select 2 optimal cut points using the AddFor algorithm. Correct the AUC
  res.addfor.k2 <- catpredi(formula = y ~ 1, cat.var = "x", cat.points = 2, 
  data = df, method = "addfor", range=NULL, correct.AUC=TRUE, 
  control=controlcatpredi(addfor.g=100))
  # Select 3 optimal cut points using the AddFor algorithm. Correct the AUC
  res.addfor.k3 <- catpredi(formula = y ~ 1, cat.var = "x", cat.points = 3, 
  data = df, method = "addfor", range=NULL, correct.AUC=TRUE, 
  control=controlcatpredi(addfor.g=100))     
  # Select optimal number of cut points
  comp <-  comp.cutpoints(res.addfor.k2, res.addfor.k3, V = 100)
# }