Section: New Results
Clustering and variable selection in regression
Participants : Christophe Biernacki, Loïc Yengo, Julien Jacques.
A new framework is proposed to address the issue of simultaneous linear regression and clustering of predictors where regression coefficients are assumed to be drawn from a Gaussian mixture distribution. Prediction is thus performed using the conditional distribution of the regression coefficients given the data, while clusters are easily derived from posterior distribution in groups given the data. This work is now published in [27] . Furthermore, an R package (clere) is available on Rforge (see 5.2 ) and an improved version of the initial model has been submitted to an international journal [52] .