Re: [R] Help with gamm errors

Rob, Thanks for sending the example... > > m1=gamm(present~s(week,bs="cc")+s(week,bs="cc",by=y1),random=list(garden=~1 >) , > correlation=corAR1(form=~1|garden),family=binomial,data=count.data2) > > (ie removing the week term). This model proceeds - to a point... > > Maximum number of PQL itera

Re: [R] Help with gamm errors

Rob, It might be worth upgrading at least mgcv and MASS to the current versions (latest mgcv is 1.3-28, just gone to CRAN). Way back I vaguely remember that there was an issue with glmmPQL (called by gamm) not picking up correlation structure variables from the dataframe, but I can't now find