Error in Surv(time, status) : Time variable is not numeric

Dear,

I want to analyze two-level survival data using a shared frailty model,
for which I want to use the R package 'Frailtypack", proposed by Rondeau
et al. The dataset was built using SAS software. I also tried to change
the format using SPSS and Excell. 

My (reduced) dataset has following column names:
ID     entry    time    status    family     var1

I used following command:

frailtyPenal(Surv(time, status) ~var1 + cluster(family), Frailty=TRUE
,n.knots=8, kappa1=1500,

+ cross.validation=FALSE)

And got this error :
Error in Surv(time, status) : Time variable is not numeric
In addition: Warning message:
In is.na(time) : is.na() applied to non-(list or vector) of type 'closure'

I think R transforms the data when importing into R, so that the
observations are not numeric anymore.

Does anyone know how to handle this problem?

Thanks,

Marie

R is finding the R function 'time' rather than your variable time in your
dataset.  Perhaps adding 'data=mydata' to your function call will resolve
your issue.

Chris


Braem M wrote:

Dear,

I want to analyze two-level survival data using a shared frailty model,
for which I want to use the R package 'Frailtypack", proposed by Rondeau
et al. The dataset was built using SAS software. I also tried to change
the format using SPSS and Excell. 

My (reduced) dataset has following column names:
ID     entry    time    status    family     var1

I used following command:

frailtyPenal(Surv(time, status) ~var1 + cluster(family), Frailty=TRUE
,n.knots=8, kappa1=1500,

+ cross.validation=FALSE)

And got this error :
Error in Surv(time, status) : Time variable is not numeric
In addition: Warning message:
In is.na(time) : is.na() applied to non-(list or vector) of type
'closure'

I think R transforms the data when importing into R, so that the
observations are not numeric anymore.

Does anyone know how to handle this problem?

Thanks,

Marie

R is finding the R function 'time' rather than your variable time in your
dataset.  Perhaps adding 'data=mydata' to your function call will resolve
your issue.

Chris


Braem M wrote:

Dear,

I want to analyze two-level survival data using a shared frailty model,
for which I want to use the R package 'Frailtypack", proposed by Rondeau
et al. The dataset was built using SAS software. I also tried to change
the format using SPSS and Excell. 

My (reduced) dataset has following column names:
ID     entry    time    status    family     var1

I used following command:

frailtyPenal(Surv(time, status) ~var1 + cluster(family), Frailty=TRUE
,n.knots=8, kappa1=1500,

+ cross.validation=FALSE)

And got this error :
Error in Surv(time, status) : Time variable is not numeric
In addition: Warning message:
In is.na(time) : is.na() applied to non-(list or vector) of type
'closure'

I think R transforms the data when importing into R, so that the
observations are not numeric anymore.

Does anyone know how to handle this problem?

Thanks,

Marie