[R-sig-ME] nested random effects in nlme

[Michael Li]

I'm trying to fit a four-parameter logistic model using nlme with
nested random effects. I use something like:

fits <- nlme (y ~ SSfpl (x, A, B, xmid, scal),
                     random = A + xmid ~ 1,
                     group = ~ subject / plate,
                     fixed = A + B + xmid + scal ~ 1,
                     data = mydata,
                     start = c(A = 600, B = 5, xmid = 10, scal = 1))

However, I kept getting the error

Error in names(reSt) <- namGrp :
  'names' attribute [2] must be the same length as the vector [1]

I look into the code nlme.formula() and there is an assignment

names (reSt) <- namGrp,

which is causing the trouble when namGrp has length of 2 instead of 1.

Did I do something wrong? How do you use nested random effects in nlme?

Best, Michael