drc (version 4.0-0)

anova.drc: ANOVA for dose-response model fits

Description

'anova' produces an analysis of variance table for one or two non-linear model fits.

Usage

# S3 method for drc
anova(object, ..., details = TRUE, test = NULL)

Value

An object of class 'anova'.

Arguments

object

an object of class 'drc'.

...

additional arguments.

details

logical indicating whether or not details on the models compared should be displayed. Default is TRUE (details are displayed).

test

a character string specifying the test statistic to be applied. Use "od" to assess overdispersion for binomial data.

Author

Christian Ritz

Details

If a single object is specified a message is suggesting to use the function modelFit for test of lack-of-fit, comparing the dose-response model to a more general one-way or two-way ANOVA model.

If two objects are specified a test for reduction from the larger (more general) model to the smaller, reduced model is given. This only makes sense if the models are nested: the reduced model is a submodel of the larger model.

References

Bates, D. M. and Watts, D. G. (1988) Nonlinear Regression Analysis and Its Applications, New York: Wiley and Sons (pp. 103--104)

See Also

For comparison of nested or non-nested model the function mselect can also be used.

The function anova.lm for linear models.

Examples

## Comparing a four-parameter Weibull type 1 model 
##  to a reduced three-parameter Weibull type 1 using an F test
ryegrass.m1 <- drm(rootl ~ conc, data = ryegrass, fct = W1.4())
ryegrass.m2 <- drm(rootl ~ conc, data = ryegrass, fct = W1.3())
anova(ryegrass.m2, ryegrass.m1)  
# reduction to 'W1.3' not possible (highly significant)   

anova(ryegrass.m2, ryegrass.m1, details = FALSE)  
# not showing details