Full_Name: Emmanuel Charpentier Version: R version 2.9.0 (2009-04-17) - i486-pc-linux-gnu OS: Linux xxxxxx 2.6.28-11-generic #42-Ubuntu SMP Fri Apr 17 01:57:59 UTC 2009 i686 GNU/Linux Submission from: (NULL) (164.2.255.244) The "df.residual" component of an rlm object exists but carries NA. Curiously, the "df" component of a summary.rlm object exists, and carries 3 values (the manpage made me expect two : model and residual DFs). As usual : sessionInfo() R version 2.9.0 (2009-04-17) i486-pc-linux-gnu locale: LC_CTYPE=fr_FR.UTF-8;LC_NUMERIC=C;LC_TIME=fr_FR.UTF-8;LC_COLLATE=fr_FR.UTF-8;LC_MONETARY=C;LC_MESSAGES=fr_FR.UTF-8;LC_PAPER=fr_FR.UTF-8;LC_NAME=C;LC_ADDRESS=C;LC_TELEPHONE=C;LC_MEASUREMENT=fr_FR.UTF-8;LC_IDENTIFICATION=C attached base packages: [1] stats graphics grDevices datasets utils methods base other attached packages: [1] mice_1.21 nnet_7.2-46 lme4_0.999375-28 Matrix_0.999375-26 [5] MASS_7.2-46 odfWeave_0.7.10 XML_2.3-0 lattice_0.17-22 loaded via a namespace (and not attached): [1] grid_2.9.0 tools_2.9.0 Self-contained reproductible example :> set.seed(1066) # and all that.. > p1<-rlm(y~f1 * f2 + x,data=within(data.frame(f1=as.factor(sample(c("a","b","c"),200,TRUE)), f2=as.factor(c("x","y","z","t")[sample(1:4,20,TRUE)]), x=runif(200,0,4)),{y=2*(f1=="b")-3*(f2=="y")+20*((f1=="b")&(f2=="y"))+rchisq(200,3)}))> p1$df.residual[1] NA # Ouch !> summary(p1)$df[1] 13 187 13 # Aiieeee !