Methods in parametric cluster analysis commonly assume data can be modelled by means of a finite mixture of distributions. However, associating each mixture component to one cluster is frequently misleading because different mixture components can overlap, and then, associated clusters can overlap too suggesting a unique cluster. A number of approaches have already been proposed to construct the clusters by merging components using the posterior probabilities. This article presents a generic approach for building a hierarchy of mixture components that integrates and generalizes some techniques proposed earlier in the literature. Using this proposal, two new techniques based on the log-ratio of posterior probabilities are introduced. Moreover, to decide the final number of clusters, two new methods are presented. Simulated and real datasets are used to illustrate this methodology.
AitchisonJ (1986). The statistical analysis of compositional data (Monographs on statistics and applied probability). London: Chapman & Hall Ltd. Reprinted with additional material, Caldwell, NJ: The Blackburn Press, 2003.
2.
AitchisonJ (2002) Simplicial inference. Algebraic Methods in Statistics and Probability, 287, 1–22.
3.
BaudryJPRafteryAECeleuxGLoKGottardoR (2010) Combining mixture components for clustering. Journal of Computational and Graphical Statistics, 19, 332–53.
4.
BenagliaTChauveauDHunterDRYounR (2009) mixtools: An R package for analyzing finite mixture models. Journal of Statistical Software, 32, 1–29.
5.
Comas-CufíMMartín-FernándezJAMateu-FiguerasG (2016) Logratio methods in mixture models for compositional data sets. SORT, 40, 349–74.
6.
FraleyCRafteryAE (1998) How many clusters? Answers via model-based cluster analysis. The Computer Journal, 41, 578–88.
7.
FraleyCRafteryAE (2002) Model-based clustering, discriminant analysis, and density estimation. Journal of the American Statistical Association, 97, 611–31.
8.
FreyBJDueckD (2007) Clustering by passing messages between data points. Science, 315, 972–76.
9.
HambyD (1994) A review of techniques for parameter sensitivity analysis of environ- mental models. Environmental Monitoring and Assesment, 32, 135–54.
10.
HennigC (2010) Methods for merging Gaussian mixture components. Advances in Data Analysis and Classification, 4, 3–34.
11.
KeribinC (1998) Consistent estimate of the order of mixture models. Comptes Rendues de l'Academie des Sciences, Série I-Mathématiques, 326, 243–48.
12.
KeribinC (2000) Consistent estimation of the order of mixture models. Sankhyā: The Indian Journal of Statistics, Series A, 62, 49–66.
13.
LeeHJChoS (2004) Combining Gaussian mixture models. In Intelligent Data Engin- eering and Automated Learning–IDEAL 2004 SE–98, edited by Z Yang, H Yin and R Everson. Volume 3177 of Lecture Notes in Computer Science, pages 666–71. Exeter, UK: Springer Berlin Heidelberg.
14.
LongfordNTBartošováJ (2014) A confusion index for measuring separation and clustering. Statistical Modelling, 14, 229–55.
15.
MaitraRMelnykovV (2010) Simulating data to study performance of finite mixture modelling and clustering algorithms. Journal of Computational and Graphical Statistics, 19, 354–76.
16.
Martín-FernándezJADaunis-i-EstadellaJMateu-FiguerasG (2015) On the interpre- tation of differences between groups for compositional data. SORT, 39, 231–52.
17.
Martín-FernándezJAThio-HenestrosaS (editors) (2016) The compositional data analysis: CoDaWork, L'Escala, Spain, June 2015. Springer Proceedings in Mathematics & Statistics, 187. New York, NY: Springer International Publishing.
18.
McLachlanGJRathnayakeS (2014) On the number of components in a Gaussian mixt- ure model. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 4, 341–55.
19.
MelnykovV (2013) On the distribution of posterior probabilities in finite mixture models with application in clustering. Journal of Multivariate Analysis, 122, 175–89.
20.
MelnykovV (2016) Merging mixture components for clustering through pairwise overlap. Journal of Computational and Graphical Statistics, 25, 66–90.
21.
MelnykovVChenWCMaitraR (2012) MixSim: An R package for simulating data to study performance of clustering algorithms. Journal of Statistical Software, 51, 1–21.
22.
MilliganGWCooperMC (1985) An examination of procedures for determining the number of clusters. Psychometrika, 50, 159–79.
23.
Palarea-AlbaladejoJMartín-FernándezJA (2015) zCompositions: R packages for multivariate imputation of nondetecteds and zeros in compositional data sets. Chemometrics and Intelligent Laboratory Systems, 143, 85–96.
24.
Palarea-AlbaladejoJMartín-FernándezJASotoJA (2012) Dealing with distances and transformations for fuzzy C-means clustering of compositional data. Journal of Classification, 29, 144–69.
25.
PastoreATonellatoSF (2013) A merging algorithm for Gaussian mixture components (Series No. 04/WP/2013). [SSRN Electronic Journal]. Department of Economics Research Paper, University Ca’ Foscari of Venice. URL http://papers.ssrn.com/sol3/papers. (last accessed on 23 November 2017).
26.
Pawlowsky-GlahnVEgozcueJJ (2001) Geometric approach to statistical analysis on the simplex. SERRA, 15, 384–98.
27.
PunzoA (2014) Flexible mixture modelling with the polynomial Gaussian cluster-weighted model. Statistical Modelling, 14, 257–91.
28.
R Development Core Team (2015) R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing. URL http://www.r-project.org (last accessed on 23 November 2017).
29.
RaySLindsayBG (2005) Topography of multivariate normal mixtures. Annals of Statistics, 33, 2042–65.
30.
ScruccaLFopMMurphyTBRafteryAE (2016) mclust 5: Clustering, classification and density estimation using Gaussian finite mixture models. R Journal, 8, 289–317.
