- Abstract: We are concerned in clustering continuous data sets subject to nonignorable missingness. We per- form clustering with a specific semi-parametric mixture, avoiding the component distributions and the missingness process to be specified, un- der the assumption of conditional independence given the component. Estimation is performed by maximizing an extension of smoothed likeli- hood allowing missingness. This optimization is achieved by a Majorization-Minorization algo- rithm. We illustrate the relevance of the approach by numerical experiments.
- Keywords: clustering, mixture models, nonignorable missingness, nonparametric mixture