Search
Now showing items 1-10 of 21
-
Model-based clustering of gaussian copulas for mixed data
Communications in statistics. theory and methods, 01-01-2017, 46, 11635-11656Article dans une revue scientifique -
Pitfalls in Mixtures from the Clustering Angle
Working Group on Model-Based Clustering Summer Session, Paris, 17-07-2016, 17-07-2016Autre communication scientifique (congrès sans actes - poster - séminaire...) -
A targeted multi-partitions clustering
The 11th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics 2018), Pise, 14-12-2018, 14-12-2018Autre communication scientifique (congrès sans actes - poster - séminaire...) -
Model-based clustering for conditionally correlated categorical data
Journal of Classification, Springer Verlag, 2015, 2 (32), 145-175Article dans une revue scientifiquefulltext -
An efficient SEM algorithm for Gaussian Mixtures with missing data
8th International Conference of the ERCIM WG on Computational and Methodological Statistics, Londres, 12-12-2015Autre communication scientifique (congrès sans actes - poster - séminaire...) -
Reject inference methods in credit scoring
Journal of Applied Statistics, 2021, 48 (13-15), p. 2734-2754Article dans une revue scientifiquefulltext -
Dealing with missing data through mixture models
ICB Seminars 2017 - 154th Seminar on ”Statistics and clinical practice”, Varsovie, 11-05-2017, 11-05-2017Communication dans un congrès avec actesfulltext -
Model-based clustering of Gaussian copulas for mixed data
Communications in Statistics - Theory and Methods, Taylor & Francis, 2017, 46 (23), 11635-11656Article dans une revue scientifiquefulltext -
Réintégration des refusés en Credit Scoring
49e Journées de Statistique, Avignon, 29-05-2017Autre communication scientifique (congrès sans actes - poster - séminaire...)fulltext -
A predictive deviance criterion for selecting a generative model in semi-supervised classification
Computational Statistics and Data Analysis, Elsevier, 2012Article dans une revue scientifique