Fit a Nonlinear Mixed Effects Model
DESCRIPTION:
This function is generic; methods functions can be written to handle specific classes of objects. Classes which already have methods for this function include formula and nlsList.
USAGE: 
nlme(object, fixed, random = fixed, cluster, data = sys.parent(),
     start, est.method = c("ML", "RML"), re.block, re.structure =
     c("unstructured", "diagonal", "identity", "compsymm", "ar1"),
     re.paramtr = c("matrixlog", "cholesky", "spherical", "logcholesky",
     "givens"),  serial.structure = c("identity", "ar1",
     "ar1.continuous", "compsymm", "ar2", "ma1", "ma2",
     serial.covariate = NULL,
     serial.covariate.transformation = c("rank.within.cluster", "none",
     "round", "global.rank"), var.function = c("identity", "power",
     "expon", "cte.power", "cte.expon"), var.covariate = NULL,
     var.estimate = T, control, na.action = na.include, na.pattern,
     verbose = F)
REQUIRED ARGUMENTS:
object:
either a formula specifying a nonlinear model for the response, or an object inheriting from class nlsList.
OPTIONAL ARGUMENTS:
others:
see the helpfile for nlme.formula().
VALUE:
an object of class nlme representing the fit. Generic functions such as print(), plot(), predict(), and summary() have methods to show the results of the fit. See nlme.object for the components of the fit. The functions residuals(), coefficients() and fitted.values() can be used to extract some of its components.
SEE ALSO:
nlme.formula , nlme.nlsList , nlme.object .
EXAMPLES: 
See the helpfiles for nlme.formula() and nlme.nlsList().