drc (version 1.0-3)

mixdrc: Fitting multiple dose-response curves with random effects

Description

'mixdrc' fits non-linear mixed models where random effects are assigned to some or all of the parameters.

Usage

mixdrc(object, random, data, startVal)

Arguments

object

an object of class 'drc'.

random

a character string specifying the random effects. Specification is as in nlme.

data

a data frame containing the variables in the model (not optional).

startVal

a numeric vector of initial parameter values for the fixed effects (optional).

Value

• An object of classes 'drc' and 'nlme'.

Details

The function searches through a range of initial values in order to obtain convergence of the estimation procedure.

Examples

## NOTICE: The examples do not work in R 2.4.0!!!
## They will be working in future versions of R.
## If you need this functionality you have to use an 
## older version of R for the time being

## First fitting a model without random effects
# model1 <- multdrc(SLOPE~DOSE, CURVE, data=PestSci,
# collapse=data.frame(HERBICIDE, 1, 1, HERBICIDE))

## Then fitting the same model (the same fixed effects)
##  but with random effects (assigned to d)
# model2 <- mixdrc(model1, random="d~1|CURVE", data=PestSci)
# compParm(model2, "e", "-")

## Fitting a model without random effects
##  but with a Box-Cox transformation
## model3 <- multdrc(SLOPE~DOSE, CURVE, data=PestSci,
## collapse=data.frame(HERBICIDE, 1, 1, HERBICIDE), boxcox=TRUE)

## Then fitting the same model with random effects assigned to d
## model4 <- mixdrc(model3, random="d~1|CURVE", data=PestSci)
## compParm(model4, "e", "-")

## Fitting a model without random effects, but fixing the c parameter at 0
## model5 <- multdrc(SLOPE~DOSE, CURVE, data=PestSci,
## collapse=data.frame(HERBICIDE, 1, 1, HERBICIDE), boxcox=TRUE,
## fct=l4(fixed=c(NA,0,NA,NA)))

## Fitting the corresponding mixed model with random effects on d
## model6 <- mixdrc(model5, random="d~1|CURVE", data=PestSci)

## rm(model1, model2, model3, model4, model5, model6)