________________________________
De: Douglas Bates<bates at stat.wisc.edu>
CC: r-sig-mixed-models at r-project.org
Enviado: mi?,8 junio, 2011 18:14
Asunto: Re: [R-sig-ME] Variable () converted to a factor
Could you please send us the output from
library(lme4)
sessionInfo()
# whatever you do to attach your data
str(inslarge)
str('tlengthcoef)
ote:
Hello, list:
I am trying to implement a model with lmer. The dependent variable is
different insect abundances for different sites, and the explanatory variables
are several coefficients of variation for the intensity of different sexual
signals shown by swallows nesting in those sites. Measures were taken in two
different years, so I included "year" as a random factor. As I was getting an
error message, I decided to simplify the amalysis just to check were the
problem
could be. Still with the simplest possible analysis:
insectmodel2<-lmer(inslarge~tlengthcoef+(1|year))
I still get this message (sorry some parts are in Spanish, I don't know how
to change that):
Mensajes de aviso perdidos
1: In model.matrix.default(mt, mf, contrasts) :
variable 'inslarge' converted to a factor
2: In model.matrix.default(mt, mf, contrasts) :
variable 'tlengthcoef' converted to a factor
3: In function (fr, FL, start, REML, verbose) :
NAs introducidos por coerci?n (NAs introduced by coercion
It's funny that it converts my variables to factors when I've been
struggling
for that not to happen when attaching the data set.
Anyone can help me explain and deal with this problem? Thank you very much!
Iker
[[alternative HTML version deleted]]
_______________________________________________
R-sig-mixed-models at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
[[alternative HTML version deleted]]
_______________________________________________
R-sig-mixed-models at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models