Variable Selection for model-based clustering managed by the Latent Class Model. This model analyses mixed-type data (data with continuous and/ or count and/or categorical variables) with missing values (missing at random) by assuming independence between classes. The one-dimensional marginals of the components follow standard distributions for facilitating both the model interpretation and the model selection. The variable selection is led by an alternated optimization procedure for maximizing the MICL criterion. The maximum likelihood inference is done by an EM algorithm for the selected model. This package also performs the imputation of missing values by taking the expectation of the missing values conditionally on the model, its parameters and on the observed variables.
|Author||Matthieu Marbac and Mohammed Sedki|
|Date of publication||2016-07-13 15:42:57|
|Maintainer||Mohammed Sedki <email@example.com>|
|License||GPL (>= 2)|
summary-methods: Summary function.
VarSelCluster: This function performs the variable selection and the maximum...
VarSelLCM-package: Variable Selection in model-based clustering managed by the...
VSLCMcriteria-class: Constructor of ['VSLCMcriteria'] class
VSLCMmodel-class: Constructor of ['VSLCMmodel'] class
VSLCMparamCategorical-class: Constructor of ['VSLCMparamCategorical'] class
VSLCMparamContinuous-class: Constructor of ['VSLCMparamContinuous'] class
VSLCMparamInteger-class: Constructor of ['VSLCMparamInteger'] class
VSLCMparamMixed-class: Constructor of ['VSLCMparamMixed'] class
VSLCMpartitions-class: Constructor of ['VSLCMpartitions'] class
VSLCMresultsCategorical-class: Constructor of ['VSLCMresultsCategorical'] class
VSLCMresultsContinuous-class: Constructor of ['VSLCMresultsContinuous'] class
VSLCMresultsInteger-class: Constructor of ['VSLCMresultsInteger'] class
VSLCMresultsMixed-class: Constructor of ['VSLCMresultsMixed'] class
VSLCMstrategy-class: Constructor of ['VSLCMstrategy'] class