Rankcluster-package: Model-Based Clustering for Multivariate Partial Ranking Data

In Rankcluster: Model-Based Clustering for Multivariate Partial Ranking Data

Description

This package proposes a model-based clustering algorithm for ranking data. Multivariate rankings as well as partial rankings are taken into account. This algorithm is based on an extension of the Insertion Sorting Rank (ISR) model for ranking data, which is a meaningful and effective model parametrized by a position parameter (the modal ranking, quoted by mu) and a dispersion parameter (quoted by pi). The heterogeneity of the rank population is modelled by a mixture of ISR, whereas conditional independence assumption is considered for multivariate rankings.

Details

The main function is rankclust.

Author(s)

Maintainer: Quentin Grimonprez <[e-mail]>

References

[1] C.Biernacki and J.Jacques (2013), A generative model for rank data based on sorting algorithm, Computational Statistics and Data Analysis, 58, 162-176.

[2] J.Jacques and C.Biernacki (2012), Model-based clustering for multivariate partial ranking data, Inria Research Report n 8113.

Examples

# see vignette
# vignette("Rankcluster")

# main function of the package for run the algorithm
data(big4)
result = rankclust(big4$data, K = 2, m = big4$m, Ql = 200, Bl = 100, maxTry = 2)
 

Example output

WARNING : Since Rancluster 0.92, the ranks have to be given to the package in the ranking notation (see convertRank function), with the following convention :
- missing positions are replaced by 0
- tied are replaced by the lowest position they share

 for K= 2 clusters, the algorithm has not converged (a proportion was equal to 0 during the process), please retry
No convergence for all values of K (a proportion was equal to 0 during the process). Please retry

Rankcluster documentation built on Aug. 26, 2019, 3 p.m.