[R-sig-ME] specifying random effects in nlme with correlation fixed at 0

[Kenneth KNOBLAUCH]

I'm fitting a model using nlme.  The data frame has 9600 rows and the grouping variable, Obs, has 10 levels.  I fit the following model (names of variables simplified from original) that runs fine:

m1 <- nlme(y ~ A * x / (x + B), data = d.df,
                   fixed = A + B ~ F,  
                   random = A + B ~ 1 | Obs,
                   start = list(fixed = c(A = c(2, 0), B = c(15, 0)) ))

F is a 2 level factor and A and B parameters to estimate.  This runs fine, too, using SSmicmen(x, A, B) for the right hand side of the formula.  x and y are numeric variables.

I would like to compare model m1 to a model where the correlation between random effects is fixed to 0.  I tried

update(m1, random = list(A ~ 1 | Obs, B ~ 1 | Obs))

but I get the following error message:

Error in parse(text = paste("~", paste(nVal, collapse = "/"))) : 
  <text>:2:0: unexpected end of input
1: ~ 
   ^

I've also tried with various combinations of the pdMat functions but can't find the right way to specify this. 

Simpler models, leaving out one or the other random effect work as well as for leaving out fixed effects after the random effects have been tested. 

Thank you for any suggestions.

Ken
  ___
  Kenneth Knoblauch
 Inserm U1208
 Stem-cell and Brain Research Institute
 18 avenue du Doyen Lépine
 69500 Bron
 France
 tel: +33 (0)4 72 91 34 77
 fax: +33 (0)4 72 91 34 61
 portable: +33 (0)6 84 10 64 10
 https://sbri.fr/public-profile/63/single-member/