R: checking model assumptions with nlme

Question

library(nlme)
fm1 <- nlme(height ~ SSasymp(age, Asym, R0, lrc),
            data = Loblolly,
            fixed = Asym + R0 + lrc ~ 1,
            random = Asym ~ 1,
            start = c(Asym = 103, R0 = -8.5, lrc = -3.3))

I am fitting a nonlinear mixed effects model using the nlme package in R. And I want to perform model diagnostics and check the assumptions that the 1) errors are normally distributed and that the 2) random effects are normally distributed.

For 1), I can just do a simple scatterplot of the residuals

qqnorm(fm1$residuals)

But how do I check that the random effects are also normally distributed?

Answer 1

You can extract random effect by using generic function ranef (or random.effects). Particularly, the effect you want is

oo <- ranef(fm1)$Asym

Now you may use a QQ plot to check normality:

qqnorm(oo)
qqline(oo)