Mice pool () and coxph () function: in mice.df (...): large sample expected?

I was using coxph () from the survival package on multiple imputed datasets and ran into a warning when trying to combine the results. The warning message says: "In mice.df (m, lambda, dfcom, method): Large sample accepted.

Below is a reproducible example (with public data, without worrying about using both mice and coxph - this data):

library(mice)
library(survival)

#load publically available data
data(pbc)

#select variables for the reproducable example
pbc.select <- pbc[pbc$status %in% c(0,1) , c("id", "time", "status", "trt")]

imp <- mice(pbc.select) #impute trt
fit <- with(imp, coxph(Surv(time, status) ~ trt)) #fit coxph in each imp
pool(fit) #pool the models; get the error

      

        
        
        
      

    

This warning is similar to the pool () function trying to require dfcom from

dfcom <- df.residual(object)

      

        
        
        
      

    

where df.residual () does not apply to the object specified in this context, which is of class "coxph"

class(fit) # "mira" "matrix" 
class(fit$analyses[[1]]) "coxph"

      

        
        
        
      

    

My questions are: 1) I am using the correct syntax for the target 2) if so, is there a way to provide pool () with relevant information? 3) how does this assumption affect the results?