Version: 0.9.2
Date: 2019-09-13
Title: Analysis of Competing Risks Using Quantile Regressions
Author: Stephan Dlugosz [aut, cre], Limin Peng [aut], Ruosha Li [aut], Shuolin Shi [ctb]
Maintainer: Stephan Dlugosz <stephan.dlugosz@googlemail.com>
Depends: R (≥ 2.13.0)
Imports: graphics, quantreg, stats, survival
Description: Estimation, testing and regression modeling of subdistribution functions in competing risks using quantile regressions, as described in Peng and Fine (2009) <doi:10.1198/jasa.2009.tm08228>.
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
Repository: CRAN
ByteCompile: TRUE
URL: https://bitbucket.org/sdlugosz/cmprskqr
BugReports: https://bitbucket.org/sdlugosz/cmprskqr/issues
Packaged: 2019-09-15 14:23:15 UTC; Stephan
Date/Publication: 2019-09-15 14:50:03 UTC

Competing Risks Quantile Regression

Description

quantile regression modeling of subdistribution functions in competing risks

Usage

crrQR(ftime, fstatus, X, failcode=1, cencode=0, 
tau.range=c(0.01,0.99), tau.step=0.01, subset, 
na.action=na.omit, rq.method="br", variance=TRUE)

## S3 method for class 'crrQR'
print(x, ...)

Arguments

ftime

vector of failure/censoring times

fstatus

vector with a unique code for each failure type and a separate code for censored observations

X

matrix (nobs x ncovs) of covariates

failcode

code of fstatus that denotes the failure type of interest

cencode

code of fstatus that denotes censored observations

tau.range

vector of length 2 denoting the range of quantiles

tau.step

grid size on tau.range (spacing between two grid points)

subset

a logical vector specifying a subset of cases to include in the analysis

na.action

a function specifying the action to take for any cases missing any of ftime, fstatus, cov1, cov2, cengroup, or subset.

rq.method

method of computation for quantile regressions. (cf. documentation of method rq.fit in package quantreg for details.)

variance

if FALSE, then suppresses computation of asymptotic variances

x

crrQR object (output from crrQR()) for method print

...

included for compatibility with the generic functions. Not currently used.

Details

Fits the competing risks quantile regression model described in Peng and Fine (2009).

While the use of model formulas is not supported, the model.matrix function can be used to generate suitable matrices of covariates from factors, eg model.matrix(~factor1+factor2)[,-1] will generate the variables for the factor coding of the factors factor1 and factor2. The final [,-1] removes the constant term from the output of model.matrix.

If variance=FALSE, then some of the functionality in summary.crrQR and print.crrQR will be lost. This option can be useful in situations where crrQR is called repeatedly for point estimates, but standard errors are not required, such as in bootstrapping the cumulative incidence function for confidence intervals.

The print method prints the estimated coefficients, the estimated standard errors, and the two-sided p-values for the test of the individual coefficients equal to 0.

A first implementation of the estimation procedure was prepared by Limin Peng and Ruosha Li.

Value

Returns a list of class crrQR, with components

$beta.seq

the estimated regression coefficients

$tau.seq

the sequence of quantiles computed

$var.seq

estimated variance covariance matrix of coef

$inf.func

list of estimated influence functions

$call

the call to crr

$n

the number of observations used in fitting the model

$n.missing

the number of observations removed from the input data due to missing values

$cvt.length

number of covariates (columns of X)

References

Peng L and Fine JP (2009) Competing risks quantile regression. JASA 104:1440-1453.

See Also

predict.crrQR plot.predict.crrQR summary.crrQR rq.fit

Examples

# simulated data to test 
set.seed(10)
ftime <- rexp(200)
fstatus <- sample(0:2,200,replace=TRUE)
X <- matrix(runif(600),nrow=200)
dimnames(X)[[2]] <- c('x1','x2','x3')
#compute model
print(z <- crrQR(ftime,fstatus,X))
summary(z)
# predict and plot cumulative incedences
reference <- as.matrix(rbind(c(.1,.5,.8),c(.1,.5,.2)))
dimnames(reference)[[2]] <- c('x1','x2','x3') 
z.p <- predict(z,reference)
print(z.p)
plot(z.p,lty=1,color=2:3)
crrQR(ftime,fstatus,X,failcode=2)

Plot estimated coefficients

Description

plot method for crrQR

Usage

## S3 method for class 'crrQR'
plot(x, subset=NULL, main=NULL, ...)

Arguments

x

output from crrQR

subset

plot a subset of coefficients

main

main title of the plot

...

other arguments to plot

Side Effects

plots the variable profiles for each curve

See Also

crrQR

Plot estimated subdistribution functions

Description

plot method for predict.crrQR

Usage

## S3 method for class 'predict.crrQR'
plot(x, lty=1:(ncol(x)-1), color=1,
ylim=c(0, max(x[, ncol(x)])), xmin=0, xmax=max(x[, -ncol(x)]), ...)

Arguments

x

output from predict.crrQR

lty

vector of line types. If length is < \# curves, then lty[1] is used for all.

color

vector of line colors. If length is < \# curves, then color[1] is used for all.

ylim

range of y-axis (vector of length two)

xmin

lower limit of x-axis (often 0, the default)

xmax

upper limit of x-axis

...

other arguments to plot

Side Effects

plots the subdistribution functions estimated by predict.crrQR, by default using a different line type for each curve

See Also

crrQR predict.crrQR

Estimate subdistribution functions from crrQR output

Description

predict method for crrQR

Usage

## S3 method for class 'crrQR'
predict(object, x, rearrangement, ...)

Arguments

object

output from crrQR

x

vector of covariate values for which the conditional distribution function is to be estimated. The columns of x must be named the same as in the original call to crrQR. Each must be given if present in the original call to crrQR.

rearrangement

set rearrangement=TRUE to perform a rearrangement of the predicted probabilities as suggested in Chernozhukov V, Fernández-Val I and Galichon A (2010).

...

additional parameters (currently ignored).

Details

Computes the conditional estimate given values of covariates from sup(\tau: \tau \leq \zeta_{x,j}^{-1}[\ln(t)]), for \zeta_{x,j}(\tau) = x'\beta_j(\tau) (see Dlugosz S, Lo S and Wilke RA (2014) for details)

Value

Returns a matrix with the unique type 1 failure times in the first column, and the other columns giving the estimated subdistribution function corresponding to the covariate combinations in the rows of x, at each failure time (the value that the estimate jumps to at that failure time).

References

Chernozhukov V, Fernández-Val I and Galichon A (2010) Quantile and probability curves without crossing. Econometrica 78, 1093-1125.

Dlugosz S, Lo S, Wilke RA (2014) Competing risks quantile regression at work: In-depth exploration of the role of public child support for the duration of maternity leave. unpublished.

See Also

crrQR plot.predict.crrQR

Summary method for crrQR

Description

generate and print summaries of crrQR output

Usage

## S3 method for class 'crrQR'
summary(object, conf.int = 0.95, digits =
max(options()$digits - 5, 2), ...)

## S3 method for class 'summary.crrQR'
print(x, digits=max(options()$digits - 4, 3), ...)

Arguments

object

an object of class crrQR (output from the crrQR function)

conf.int

the level for a two-sided confidence interval on the coefficients. Default is 0.95.

digits

in summary.crrQR, digits determines the number of significant digits retained in the p-values. In print.summary.crrQR, digits sets the values of the digits option for printing the output.

...

included for compatibility with the generic functions. Not currently used.

x

an object of class summary.crrQR (output from the summary method for crrQR)

Details

The summary method calculates the average effects, the variances and p-values of the test on the effect beeing 0. Furthermore it performs a test for constant coefficients. The print method prints a fairly standard format tabular summary of the results.

Value

summary.crrQR returns a list of class summary.crrQR, which contains components

call

the call to crr

n

the number of observations used in fitting the model

n.missing

the number of observations removed by crr from the input data due to missing values

ave.eff

vector of average effects of covariates

var.ave.eff

vector of corresponding variances

p.signf.test

p-values for testing average effect=0

cnst.test

scores of test on constant effect

var.cnst.test

variances of the score

p.cnst.test

p-values for the test

See Also

crrQR

Examples

## see examples in the crrQR help file