Novel model selection criteria on sparse biological networks

Abstract

In statistical literature, gene networks are represented by graphical models, known by their sparsity in high dimensions. In this study, we suggest novel model selection criteria, namely, ICOMP, CAIC and CAICF to apply on simulated gene networks when selecting an optimal model among alternative estimated networks’ constructions. In this description, we build models with the Gaussian graphical model (GGM) and the inference of GGM is achieved via the graphical lasso method. In the assessment of our proposed model selection criteria, we compare their accuracies with other well-known criteria in this field under various dimensions and topologies of networks.