MODAL - 2014 - Annual activity report

MODAL

MODAL - 2014

Project-Team Modal

Members

Overall Objectives

MOdel for Data Analysis and Learning

Research Program

Generative model design
Data visualization

Application Domains

Application domains

New Software and Platforms

BlockCluster package for co-clustering
clere package for high dimensional regression
Clustericat package for correlated categorical variable
CoModes package for correlated categorical variables
CorReg package for correlated variables in regression
HDPenReg package for penalized regressions in high dimension
FunFEM package for functional data
FunHDDC package for functional data
Galaxy-Modal platform
metaMA package for meta-analysis of microarray data
metaRNASeq package for meta-analysis of RNA-Seq data
MixCluster package for correlated mixed variables
MIXMOD and Rmixmod package for mixed data
MixtComp package for full mixed data
MPAgenomics package for multi-patient analysis of genomic markers
RankCluster package to cluster ranking data
rtkpp package: STK++ Integration To R Using Rcpp
STK++ release 0.8.4: The Statistical ToolKit

New Results

Highlights of the Year
Model for conditionally correlated categorical data
Model for conditionally correlated categorical data
Mixture model for mixed kind of data
Mixture of Gaussians with Missing Data
Clustering and variable selection in regression
Model-based clustering for multivariate partial ranking data
Generative models for correlated variables in regression
Model-based clustering for multivariate partial ordinal data
Clustering for functional data into discriminative subspaces
Degeneracy in multivariate Gaussian mixtures
Auto-Associative Models
Resampling and density estimation
Resampling and classification
Kernel change-point
Normality test in RKHS
Differential meta-analysis of RNA-seq data from multiple studies
Multi-patient analysis of genomic markers
Scan statistics for dependent data

Bilateral Contracts and Grants with Industry

Arcelor-Mittal
PGXIS
RougeGorge
Auchan
Cap Gemini
PIXEO
AGLAE
Alicante

Partnerships and Cooperations

Regional Initiatives
National Initiatives
International Initiatives

Dissemination

Promoting Scientific Activities
Teaching - Supervision - Juries
Popularization

Bibliography

Major publications
Publications of the year

Previous |

Home | Next next

Section: New Results

Normality test in RKHS

Participants : Alain Celisse, Jérémie Kellner.

In the kernel method framework, we use the MMD (maximum mean discrepancy) to derive a new goodness-of-fit test that can be used in the RKHS. When applied to the usual $R^{d}$ setting, our test does not seem too sensitive to any increase on the dimension $d$ unlike other ongoing approaches. With an infinite dimension RKHS, it exhibits a good power for a prescribed level of type-I error control.

Previous |

Home | Next next