Matthieu Marbac Website


New version of VarSelLCM is available on

This package performs cluster analysis of mixed-type data with missing values.
Algorithm for variable selection is implemented.
Results can be easily interpreted by using the Shiny application.

Journal articles

  • Marbac, M. and Patin, E. and Sedki, M. (2018). Variable selection for mixed data clustering: Application in human population genomics Journal of Classification (to appear) [R package VarSelLCM.2.1 - Package tutorial].

  • Marbac, M. and Sedki, M. (2017). A Family of Blockwise One-Factor Distributions for Modelling High-Dimensional Binary Data Computational Statistics and Data Analysis, 114, 130-145 [Journal - R package MvBinary.1.0 - Package tutorial].

  • Cheam, A.S.M., Marbac, M. and McNicholas, P.D. (2017). Model-based clustering for spatio-temporal data on air quality monitoring. Environmetrics, 8 (3) [Journal - R package SpaTimeClus.1.0].

  • Marbac, M., Biernacki, C. and Vandewalle, V. (2017). Model-based clustering of Gaussian Copulas for Mixed Data. Communications in Statistics – Theory and Methods, 46 (23) [Journal - R codes].

  • Marbac, M. and Sedki, M. (2017). Variable selection for model-based clustering using the integrated complete-data likelihood. Statistics and Computing, 27 (4), 1049–1063 [Journal - R package VarSelLCM - Package tutorial].

  • Marbac, M., Biernacki, C. and Vandewalle, V. (2016). Finite mixture model of conditional dependencies modes to cluster categorical data. Advances in Data Analysis and Classification, 10 (2), 183-207 [Journal - R codes].

  • Marbac, M. and McNicholas, P.D. (2016). Dimension reduction for clustering. Wiley StatsRef : Statistics Reference Online, 1–7, [Journal]

  • Marbac, M., Tubert-Bitter, P. and Sedki, M. (2016). Bayesian model selection in logistic regression for the detection of adverse drug reactions, Biomertical Journal, 58, 1376–1389, [Journal - R package MHTrajectoryR.1.0].

  • Marbac, M., Biernacki, C. and Vandewalle, V. (2015). Model-based clustering for conditionally correlated categorical data, Journal of Classification, 32 (2), 145-175 [Journal - R codes].


  • Marbac, M., and Vandewalle, V. A tractable Multi-Partitions Clustering.

  • Marbac, M., Sedki, M., Boutron-Ruault, M.C., and Dumas, O. Patterns of cleaning product exposures using a novel clustering approach for data with correlated variables.

  • Marbac, M. and Sedki, M. VarSelLCM: an R/C++ package for variable selection in model-based clustering of mixed-data with missing values

Works in progress

  • Empirical likelihood for conditional estimating equations (with Patilea, V.)

  • Gaussian-Based Visualization of Gaussian and Non-Gaussian Model-Based Clustering (with Biernacki, C. and Vandewalle, V.)

  • Multiple model-based clustering to improve model-based prediction (with Biernacki, C., Sedki, M., and Vandewalle, V.)


  • M. Marbac, C. Biernacki and V. Vandewalle (2014). Mixture model of Gaussian copulas to cluster mixed-type data, Proceedings CompStat2014. [Pdf].

Other document

  • M. Marbac (2014). Model-based clustering for categorical and mixed variables. Thèse de doctorat [Pdf].