Section: New Results
Generative models for correlated variables in regression
Participants : Christophe Biernacki, Clément Théry.
Linear regression outcomes (estimates, prevision) are known to be damaged by highly correlated covariates. However most modern datasets are expected to mechanically convey more and more highly correlated covariates due to the global increase of the amount of variables they contain. We propose to explicitly model such correlations by a family of linear regressions between the covariates. It leads to a particular generative model through the distribution explicitly introduced between correlated covariates. It has been presented to a conference [32] and is currently written as a research paper [51] . Furthermore, an R package (CorReg) is available on CRAN (see 5.5 ). Extension is now available for missing covariables also. It is a joint work with Gaétan Loridant.