Displaying 1 result from an estimated 1 matches for "mod2b".
Did you mean:
mod2
2005 Feb 01
3
polynomials REML and ML in nlme
...be of general interest.
If I fit a fixed effect with an added quadratic term and then do it as
an orthogonal polynomial using maximum likelihood I get the expected
result- they have the same logLik.
mod2a<-lme(wthole~nplants+I(nplants^2),data=d3,random=~1|field/subplot,m
ethod="ML")
mod2b<-lme(wthole~poly(nplants,2),data=d3,random=~1|field/subplot,method
="ML")
> anova(mod2a,mod2b)
Model df AIC BIC logLik
mod2a 1 6 6698.231 6723.869 -3343.116
mod2b 2 6 6698.231 6723.869 -3343.116
However if I fit the two models by REML they are not co...