6533b82afe1ef96bd128bd2b

RESEARCH PRODUCT

Variable selection in mixed models: a graphical approach

Mariangela Sciandra

subject

Graphical representation Mixed models Model selection Penalized Weighted Residual Sum of Squares

description

Model selection can be defined as the task of estimating the performance of dif- ferent models in order to choose the (approximate) best one. The purpose of this article is to introduce an extension of the graphical representation of deviance proposed in the framework of classical and generalized linear models to the wider class of mixed models. The proposed plot is useful in determining which are the important explanatory variables conditioning on the random effects part. The applicability and the easy interpretation of the graph are illus- trated with a real data examples.

http://hdl.handle.net/10447/96346