I have a dependent variable: rtln (log transformed reaction time) >>3 predictors: choicenum (ranging from 1 to 6) ifrelevant (0 and 1) condition (0 and 1) and I have a variable with subject IDs. I would like to estimate a model where choicenum are nested within subjects . I use the following notation: >>lmer(rtln~choicenum + ifrelevant + condition + (1|subject/choicenum) for some reason this estimates 5 fixed effects for choicenum. >>Here's the output: http://dl.dropbox.com/u/22681355/output.tiff >>>Here's the dataset: http://dl.dropbox.com/u/22681355/data.csv >>>>Here's the stata output of what I'd like to get: http://dl.dropbox.com/u/22681355/output.docx