Hi everybody,
I'm trying to select a model with the function step. It is a mixed
generalized linear model fitted by the function glmmML. I have one random
variable (id), one response variable (var) and many independent variables
(x1, x2, x3..). I obtain the following error:
Error in if (all(is.finite(c(n0, nnew))) && nnew != n0)
stop("number of rows
in use has changed: remove missing values?") :
missing value where TRUE/FALSE needed
But I swear that I do NOT have any NA in my database (data1). I have checked
it many times even with is.na()
My script is the following:
model<-step(glmmML(var~1,cluster = id, family = poisson,data
data1),direction=c("both"),data=data1,scope=~x1+x2+x3+x4+x5+x6+x7+x8+x9+x10)
Does anybody know where the problem could be?
Thank you in advance,
Alba
--
View this message in context:
http://r.789695.n4.nabble.com/Error-with-step-and-glmmML-tp4095404p4095404.html
Sent from the R help mailing list archive at Nabble.com.