統計学輪講(第6回) 日時 2013年05月21日(火) 14時50分~16時30分 場所 経済学部新棟3階第3教室 講演者 Aurélie Boisbunon(JSPS外国人特別研究員) 演題:Model Selection: a decision-theoretic approach 概要 In this work we address the problem of model selection in the linear regressionframework. The objective is to determine the best predictive model based on observed data, that is, the model realizing the best tradeoff between goodness of fit and complexity. Our main contribution consists in deriving model evaluation criteria based on tools from Decision Theory, in particular loss estimation. Such criteria rely on a distributional assumption larger than the classical Gaussian one, relaxing the independence assumption and thus bringing robustness. We also propose a method for comparing model evaluation criteria through a Mean-Squared Error type measure. Our second contribution tackles the problem of constructing the models we compare. The collections of models considered here are obtained from sparse regularization methods (Lasso-type). We compare our propositions to the literature through a numerical study, in which we verify the quality of the selection.