Statistical Modelling 16 (3) (2016), 228–237
On coding effects in regularized categorical regression
Julien Chiquet
UMR MIA-Paris,
AgroParisTech—INRA—Université Paris-Saclay,
Paris,
France
e-mail: julien.chiquet@agroparistech.fr
and
UMR 8071 LaMME,
CNRS—Université d’Évry-Val-d'Essonne,
Évry,
France
Yves Grandvalet
Sorbonne universités,
Université de technologie de Compiègne,
CNRS, Heudiasyc UMR 7253,
Compiègne cedex,
France
Guillem Rigaill
Institute of Plant Sciences Paris-Saclay,
UMR 9213/UMR1403, CNRS—INRA—Université Paris-Sud,
Université d'Evry, Université Paris-Diderot,
Sorbonne Paris-Cité,
France
Abstract:
This discussion is a continuation of Tutz and Gertheiss (2016)’s paper, where we focus on the importance of the coding of effects in regularized categorical and ordinal regression. We show that, though that an appropriate regularization is profitable for any coding, the choice of a relevant coding can prevail over the one of the regularization term for revealing structures. We focus on predictors though the issues raised also apply to responses. We illustrate our point on a classic data set.
Keywords:
categorical predictor; Ordinal regression; regularization; coding system; sparsity.
back