TraMineR (version 1.1)

dissassoc: Analysis of pseudo-variance based on dissimilarity measure

Description

Compute the pseudo variance (defined by a dissimilarity measure) explained by a categorical variabel.

Usage

dissassoc(diss, group, R = 1000)

Arguments

diss

A dissimilarity matrix or a dist object (see dist)

group

The group variable

R

Number of permutation to compute the pvalue. If equal to 1, no permutation test are performed.

Value

• Return an object of class dissassoc with the following componant:
• groups
  A data.frame containing the number of case and the pseudo-variance of each group
• anova.table
  The pseudo ANOVA table
• stat
  The value of the statistics and their p-value
• perms
  The permutation object, see boot

encoding

latin1

Details

The association is based on a generalization of the principe of ANOVA to any kind of distance metric. The test return a pseudo R squared that can be interpred as a usual R squared. The statistical significance of the association is computed using permutation test. This function also perform a test of pseudo-variance homogeneity (equality of variance) using a generalization of the T statistic. There is a print method and hist method (to plot an histogramme of the significance value).

References

Studer, M., G. Ritschard, A. Gabadinho and N. S. M�ller (2009). Analyse de dissimilarit�s par arbre d'induction. Revue des Nouvelles Technologies de l'Information, EGC'2009. Batagelj, V. (1988). Generalized ward and related clustering problems. In H. Bock (Ed.), Classification and related methods of data analysis, pp. 67-74. North-Holland, Amsterdam. Anderson, M. J. (2001). A new method for non-parametric multivariate analysis of variance. Austral Ecology 26, 32-46.

See Also

dissvar to compute pseudo variance using dissimilarities and for a basic introduction to concepts of pseudo variance analysis disstree to analyse dissimilarities using induction trees dissreg to analyse dissimilarities in a way close to linear regression disscenter to compute the distance of each object to its center of group using dissimilarities

Examples

## Defining a state sequence object
data(mvad)
mvad.seq <- seqdef(mvad[, 17:86])

## Building dissimilarities
mvad.lcs <- seqdist(mvad.seq, method="LCS")

## R=1 imply no permutation test
da <- dissassoc(mvad.lcs, group=mvad$gcse5eq, R=10)
print(da)
hist(da)