Nonparametric mixture models with conditionally independent multivariate component densities

Models and algorithms for nonparametric estimation of finite multivariate mixtures have been recently proposed, where it is usually assumed that coordinates are independent conditional on the subpopulation from which each observation is drawn. Hence in these models the dependence structure comes only from the mixture. This assumption is relaxed, allowing for independent multivariate blocks of coordinates, conditional on the subpopulation from which each observation is drawn. Otherwise the density functions of these blocks are completely multivariate and nonparametric. An EM-like algorithm for this model is proposed, and some strategies for selecting the bandwidth matrix involved in the nonparametric estimation step of it are derived. The performance of this algorithm is evaluated through several numerical simulations. A real dataset of reasonably large dimension is experimented on this new model and algorithm to illustrate its potential from the model based, unsupervised clustering perspective.