A question on the lme function

[Cindy Rejwan <c.rejwan@fisheries.ubc.ca>]

Hello Splus users,

I am curretly attempting to use the lme (linear mixed effects model)
function with a dataset that contains three grouping variables: Popn, Year,
and Net.  Net is nested within Year and within Popn.  However, neither Year
nor Popn are nested.  I have made many attempts, but have not been
successful in communicating this to Splus.  The most obvious function would
seem to be:

Yfit_lme(DAge2~LakeStr+UStrAr+PctRef+Cod, random=~1|(Popn+Year)/Net,
data=dat1912)

This function returns the following error message:  Error in
getGroups.data.frame(dataMix, groups): Invalid formula for groups.

Could anyone advise me as to the appropriate notation?

Thank you very much in advance for any suggestions you may have.

Sincerely,

Cindy Rejwan