discSurv (version 1.4.1)

evalCindex: Wrapper for evaluation of discrete concordance index

Description

Convenient version to directly compute the discrete concordance without the need to use multiple functions.

Usage

evalCindex(marker, newTime, newEvent, trainTime, trainEvent)

Arguments

marker

Gives the predicted values of the linear predictor of a regression model (numeric vector). May also be on the response scale.

newTime

New time intervals in the test data (integer vector).

newEvent

New event indicators in the test data (integer vector with 0 or 1).

trainTime

Time intervals in the training data (integer vector).

trainEvent

Event indicators in the training data (integer vector with 0 or 1).

Value

Value of discrete concordance index between zero and one (numeric scalar).

References

Matthias Schmid, Gerhard Tutz and Thomas Welchowski, (2017), Discrimination Measures for Discrete Time-to-Event Predictions, Econometrics and Statistics, Elsevier, Doi: 10.1016/j.ecosta.2017.03.008

Hajime Uno and Tianxi Cai and Lu Tian and L. J. Wei, (2007), Evaluating Prediction Rules for t-Year Survivors With Censored Regression Models, Journal of the American Statistical Association

Patrick J. Heagerty and Yingye Zheng, (2005), Survival Model Predictive Accuracy and ROC Curves, Biometrics 61, 92-105

See Also

tprUnoShort, fprUnoShort, aucUno, concorIndex

Examples

# NOT RUN {
##################################################
# Example with unemployment data and prior fitting

library(Ecdat)
library(caret)
library(mgcv)
data(UnempDur)
summary(UnempDur$spell)
# Extract subset of data
set.seed(635)
IDsample <- sample(1:dim(UnempDur)[1], 100)
UnempDurSubset <- UnempDur [IDsample, ]
set.seed(-570)
TrainingSample <- sample(1:100, 75)
UnempDurSubsetTrain <- UnempDurSubset [TrainingSample, ]
UnempDurSubsetTest <- UnempDurSubset [-TrainingSample, ]

# Convert to long format
UnempDurSubsetTrainLong <- dataLong(dataSet=UnempDurSubsetTrain, 
timeColumn="spell", censColumn="censor1")

# Estimate gam with smooth baseline
gamFit <- gam(formula=y ~ s(I(as.numeric(as.character(timeInt)))) + 
s(age) + s(logwage), data=UnempDurSubsetTrainLong, family=binomial())
gamFitPreds <- predict(gamFit, newdata=cbind(UnempDurSubsetTest, 
timeInt=UnempDurSubsetTest$spell))

# Evaluate C-Index based on short data format
evalCindex(marker=gamFitPreds, 
newTime=UnempDurSubsetTest$spell, 
newEvent=UnempDurSubsetTest$censor1, 
trainTime=UnempDurSubsetTrain$spell, 
trainEvent=UnempDurSubsetTrain$censor1)

#####################################
# Example National Wilm's Tumor Study

library(survival)
head(nwtco)
summary(nwtco$rel)

# Select subset
set.seed(-375)
Indices <- sample(1:dim(nwtco)[1], 500)
nwtcoSub <- nwtco [Indices, ]

# Convert time range to 30 intervals
intLim <- quantile(nwtcoSub$edrel, prob=seq(0, 1, length.out=30))
intLim [length(intLim)] <- intLim [length(intLim)] + 1
nwtcoSubTemp <- contToDisc(dataSet=nwtcoSub, timeColumn="edrel", intervalLimits=intLim)
nwtcoSubTemp$instit <- factor(nwtcoSubTemp$instit)
nwtcoSubTemp$histol <- factor(nwtcoSubTemp$histol)
nwtcoSubTemp$stage <- factor(nwtcoSubTemp$stage)

# Split in training and test sample
set.seed(-570)
TrainingSample <- sample(1:dim(nwtcoSubTemp)[1], round(dim(nwtcoSubTemp)[1]*0.75))
nwtcoSubTempTrain <- nwtcoSubTemp [TrainingSample, ]
nwtcoSubTempTest <- nwtcoSubTemp [-TrainingSample, ]

# Convert to long format
nwtcoSubTempTrainLong <- dataLong(dataSet=nwtcoSubTempTrain, 
timeColumn="timeDisc", censColumn="rel")

# Estimate glm
inputFormula <- y ~ timeInt + histol + instit + stage
glmFit <- glm(formula=inputFormula, data=nwtcoSubTempTrainLong, family=binomial())
linPreds <- predict(glmFit, newdata=cbind(nwtcoSubTempTest, 
timeInt=nwtcoSubTempTest$timeDisc))

# Evaluate C-Index based on short data format
evalCindex(marker=linPreds, 
newTime=as.numeric(as.character(nwtcoSubTempTest$timeDisc)), 
newEvent=nwtcoSubTempTest$rel, 
trainTime=as.numeric(as.character(nwtcoSubTempTrain$timeDisc)), 
trainEvent=nwtcoSubTempTrain$rel) 

# }