error in meta-analysis for pooling AUCs

General
#1

Hello all,
I am conduting a meta-analysis to pool AUCs in two indepent studies with the random-effect model.
The codes are ass follows:

data<-read.csv("C:/Amsterdam Score.csv",header=T)
fit.AMS<-with(data5,valmeta(cstat=c.index,cstat.se=se.c.index,cstat.cilb=c.index.95CIl,cstat.ciub=c.index.95CIu,N=n,O=n.events,slab=Study))
fit.AMS

it alerts "Warning in qt((1 + level)/2, df = (k - 2)) : NaNs producing"

Can anyone help me to solve this problem?
many thanks

#2

Try conforming to the help(valmeta) example

data(EuroSCORE)
# Meta-analysis of the c-statistic (random effects)
fit <- valmeta(cstat=c.index, cstat.se=se.c.index, cstat.cilb=c.index.95CIl,
cstat.ciub=c.index.95CIu, cstat.cilv=0.95, N=n, O=n.events,
slab=Study, data=EuroSCORE)
plot(fit)

instead of using with() and see if that helps.

#3

the same error appears......

#4

How does your data layout compare to the example's? The NaN is not a number which can happen with operations like 0/0.

#5

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.