kkleinke / countimp Goto Github PK

thanks for working on this nice package!

A quick suggestion regarding the 2 level models: I think users like me could be helped by adding a check of the presence of a random effect to the 2 level models (e.g. mice.impute.2l.zinb) and a clear warning message if no random effect is found. In the current version, one receives a cryptic message

Error in parse(text = x, keep.source = FALSE) : 
  <text>:1:391: unexpected ')'

which make it difficult to get to the root of the problem.

I keep getting this error: Error in get(fn) : object 'mice.impute.21.poisson' not found
I can get it to work with just regular poisson, but I have a multilevel model. Any help is appreciated

ini=mice(dlong.simp, maxit = 0)
meth=ini$method
pred=ini$predictorMatrix
meth["risk"]= "21.poisson"
pred["risk", ]= c(-2, 1, 1, 1, 1, 1, 1, 2, 0 )

imp=countimp(data=dlong.simp, m=5, method=meth, predictorMatrix=pred, print=FALSE)