I am having difficulty in properly specifying the error structure for an experiment that is being analysed using the lme() function. Physically, I have 15 plots. Each plot contains 8 subplots. Each subplot is measured at 3 different times. One treatment variable (L), containing 3 levels, is randomly assigned to the whole plots; thus there are 5 replicate plots for each of the 3 levels of L. Two other treatment variables (K, F), each having 2 levels, are randomly assigned to the subplots within each plot; thus there are 2 replicates of each combination of K and F in each of the 15 plots. The fixed formula is y~L*K*F*time. What is the proper formula for the random effects? I had thought that it was random=~1|L/plots/subplots (i.e. subplots nested within plots nested within the L treatments) but this is wrong because, using this formula, I have no degrees of freedom for the L term. Bill Shipley Associate Editor, Ecology North American Editor, Annals of Botany Département de biologie, Université de Sherbrooke, Sherbrooke (Québec) J1K 2R1 CANADA Bill.Shipley@USherbrooke.ca <http://callisto.si.usherb.ca:8080/bshipley/> http://callisto.si.usherb.ca:8080/bshipley/ [[alternative HTML version deleted]]