I have looked through Pinheiro and Bates (2000) but have not found an explanation, so I post my question to the group. Pages 90-92 explain how the denominator df are calculated, but not why. Consider a mixed model with two predictor variables (Y, Z) in which Y only varies between groups while Z varies at both levels. The denominator df for the test of the marginal effect of Y is based on the number of groups. The denominator df for the marginal effect of Z is based on the total number of observations. I understand the logic of both. However, why is the denominator df for the interaction term (Y:Z) also based on the total number of observations?
Bill Shipley Subject Matter Editor, Ecology North American Editor, Annals of Botany Département de biologie, Université de Sherbrooke, Sherbrooke (Québec) J1K 2R1 CANADA [EMAIL PROTECTED] <http://callisto.si.usherb.ca:8080/bshipley/> http://callisto.si.usherb.ca:8080/bshipley/ [[alternative HTML version deleted]] ______________________________________________ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
