survcomp (version 1.22.0)

hr.comp.meta: Function to compare two concordance indices

Description

This function compares two lists of hazard ratios computed from the same survival data by using the function hazard.ratio. The statistical test is a Student t test for dependent samples.

Usage

hr.comp.meta(list.hr1, list.hr2, hetero = FALSE)

Arguments

list.hr1

first list of D indices as returned by the hazard.ratio function.

list.hr2

second list of D indices as returned by the hazard.ratio function.

hetero

if TRUE, a random effect model is use to compute the meta-estimators. Otherwise a fixed effect model is used.

Value

p.value

p-value from the Student t test for the comparison hr1 > hr2.

hr1

meta-estimator of the first D index.

hr2

meta-estimator of the second D index.

Details

In meta-analysis, we estimate the statistic of interest in several independent datasets. It results a list of estimates such as list of hazard ratios. The two lists of hazrd ratios must be computed from the same samples (and corresponding survival data). The function computes a meta-estimator for the correlations between the two scores and uses a Student t test for dependent samples.

References

Cochrane, W. G. (1954) "The combination of estimates from different experiments", Biometrics, 10, pages 101--129.

Haibe-Kains, B. and Desmedt, C. and Sotiriou, C. and Bontempi, G. (2008) "A comparative study of survival models for breast cancer prognostication based on microarray data: does a single gene beat them all?", Bioinformatics, 24, 19, pages 2200--2208.

See Also

concordance.index.

Examples

#first dataset
set.seed(12345)
age <- rnorm(100, 50, 10)
size <- rexp(100,1)
stime <- rexp(100)
cens <- runif(100,.5,2)
sevent <- as.numeric(stime <= cens)
stime <- pmin(stime, cens)
h1.1 <- hazard.ratio(x=age, surv.time=stime, surv.event=sevent)
h2.1 <- hazard.ratio(x=size, surv.time=stime, surv.event=sevent)
#second dataset
set.seed(54321)
age <- rnorm(110, 53, 10)
size <- rexp(110,1.1)
stime <- rexp(110)
cens <- runif(110,.55,2)
sevent <- as.numeric(stime <= cens)
stime <- pmin(stime, cens)
h1.2 <- hazard.ratio(x=age, surv.time=stime, surv.event=sevent)
h2.2 <- hazard.ratio(x=size, surv.time=stime, surv.event=sevent)
hr.comp.meta(list.hr1=list("hr.age1"=h1.1, "hr.age2"=h1.2),
  list.hr2=list("hr.size1"=h2.1, "hr.size2"=h2.2))