MLCM (version 0.3)

anova.mlcm: Analysis of Deviance for Maximum Likelihood Conjoint Measurement Model Fits

Description

Compute an analysis of deviance table for one or more maximum likelihood conjoint measurement model fits.

Usage

## S3 method for class 'mlcm':
anova(object, ..., dispersion = NULL, test = NULL)

Arguments

object, ...

objects of class mlcm, typically the result of a call to mlcm

dispersion

the dispersion parameter for the fitting family. By default, it is obtained from the object(s)

test

a character string (partially) matching one of "Chisq", "F", or "Cp". See stat.anova. Normally, "Chisq" is the appropriate value, here.

Value

• An object of class "anova" inheriting from class "data.frame".

Warning

see section Warnings in anova for warnings.

Details

See anova.glm for details. In brief, specifying a single object, results in the display of a sequential analysis of deviance table for that model. Specifying several objects, a table indicating the results of the likelihood ratio tests between successive models is displayed. The models must be nested and fit to the same data set. One can mix a formula method model with a glm model, but not more than one comparison between a pair of such models at a time.

References

Ho, Y. H., Landy. M. S. and Maloney, L. T. (2008). Conjoint measurement of gloss and surface texture. Psychological Science, 19, 196--204.

See Also

anova.glm, anova, glm

Examples

bg.add <- mlcm(BumpyGlossy)
bg.ind <- mlcm(BumpyGlossy, model = "ind", whichdim = 2)
bg.full <- mlcm(BumpyGlossy, model = "full")

anova(bg.ind, bg.add, bg.full, test = "Chisq")