Hi Cecilia, I only solve that error when I had excluded the interaction of all 3 factor. For example, if I have Treatment, Time and Cultivar, the next one works better: > anova.full.mix<-fitmaanova(madata=bnhssube, formula=~Cultivar+Treatment+Time+ Cultivar:Treatment+ Cultivar:Time+ Treatment:Time+ Sample, random=~Sample) In other hands, the next one don`t work and I got that error: > anova.full.mix<-fitmaanova(madata=bnhssube, formula=~Cultivar+Treatment+Time+ Cultivar:Treatment+ Cultivar:Time+ Treatment:Time+ Cultivar:Treatment:Time+ Sample, random=~Sample) Finish gene number 3500 ... Error in next.fix:(next.fix + ncols - 1) : NA/NaN argument May be someone can help us! If you got any help, please, share it! Best Marcelo 2008/5/5 Cecilia McGregor <cmcgre1@lsu.edu>: > Marcelo > > Dis you ever get the problem you had with the following error sorted out? > > Finish gene number 3500 ... > Error in next.fix:(next.fix + ncols - 1) : NA/NaN argument > > I'm having the same problem, but could not find a response to your > question. > > Thanks > Cecilia > > > > Cecilia McGregor, Ph.D. > Sweetpotato Breeding and Genetics Lab > School of Plant, Environmental and Soil Sciences > 236 J.C. Miller Hall > Louisiana State University > Baton Rouge > LA, 70803 > USA > > Phone: (225) 763-9138 > Fax: (225) 578-1068 > > -- Marcelo Luiz de Laia Jaboticabal - SP - Brazil sip:marcelolaia@ekiga.net <sip%3amarcelolaia@ekiga.net> "Você vê as coisas como elas são e pergunta: por quê? Mas eu sonho com coisas que nunca foram e pergunto: por que não? " - Bernard Shaw [[alternative HTML version deleted]]