Statistical Modelling 19 (6) (2019), 595–616
A clustering Bayesian approach for multivariate non-ordered circular data
Christophe Abraham,
MISTEA, Montpellier SupAgro,
INRA, Univ Montpellier,
France.
Rémi Servien,
INTHERES,
Université de Toulouse, INRA, ENVT,
Toulouse,
France.
e-mail: remi.servien@inra.fr
Nicolas Molinari,
IMAG, CNRS, Univ Montpellier,
Department of Statistics,
CHU Montpellier,
Montpellier,
France.
Abstract:
This article presents a Bayesian model for the clustering of non-ordered multivariate directional or circular data. The particular trait of our data is that each single observation is made up of k≥2 non-ordered points on the circle. We introduce a hierarchical model that combines a symmetrization technique, projected normal distributions and a Dirichlet process. One parameter is introduced to model the non-ordered trait and another one to control the variability of the angles on the circle. An informative prior on the relative locations of the k angles is also provided. The gain of the symmetrization is highlighted by a theoretical study. The parameters of the model are then inferred using a Metropolis–Hastings-within-Gibbs algorithm. Simulated datasets are analysed to study the sensitivity to hyperparameters. Then, the benefits of our approach are illustrated by clustering real data made up of the positions of five separate radiotherapy X-ray beams on a circle.
Keywords:
circular data; dirichlet process; non-ordered multivariate data; projected normal distribution; radiotherapy machine data; unsupervised clustering.
Downloads:
Example data and code in
zipped archive.
back