A focused information criterion for graphical models

8 years 6 months ago

Download feb.kuleuven.be

A new method for model selection for Gaussian Bayesian networks and Markov networks, with extensions towards ancestral graphs, is constructed to have good mean squared error properties. The method is based on the focused information criterion, and oﬀers the possibility of ﬁtting individualtailored models. The focus of the research, that is, the purpose of the model, directs the selection. It is shown that using the focused information criterion leads to a graph with small mean squared error. The low mean squared error ensures accurate estimation using a graphical model; here estimation rather than explanation is the main objective. Two situations that commonly occur in practice are treated: a datadriven full discovery of the graphical structure and the improvement of an already pre-speciﬁed feasible model. The search algorithms are illustrated by means of data examples and are compared with existing methods in a simulation study. Keywords Focused information criterion · Model se...

Eugen Pircalabelu, Gerda Claeskens, Lourens J. Wal

Real-time Traffic