drc (version 1.2-0)

mselect: Model selection

Description

Model selection by comparison of different models using 1) the maximum log likelihood value, 2) Akaike's information criteria (AIC), 3) the estimated residual variance and 4) the p-value from a lack-of-fit test as criteria.

Usage

mselect(object, fctList = NULL, nested = FALSE)

Arguments

object

an object of class 'drc'.

fctList

a list of non-linear functions to be compared.

nested

logical. TRUE results in F tests between adjacent (in 'fctList') models. Only sensible for nested models.

Value

• A matrix with one row for each model and one column for each criterion.

Details

Criterion 1) cannot be used for comparison unless the models are nested (). For criteria 2) and 3): the smaller the better; for criterion 4) the larger the better.

Examples

## Fitting initial model
m1 <- multdrc(ryegrass)

## Model selection
mselect(m1, list(l3(), l5(), W1.3(), W1.4(), weibull2(), baro5(), richards()))

mselect(m1, list(l5()))  # nested models