主  題:審計與統計

內容簡介:In this talk, we propose two sufficient variable selection procedures: one-stage and two-stage approaches using independence measures for continuous responses. Although any independence measure can be used, we use distance correlation and Hilbert-Schmidt Independence Criterion correlation to illustrate the two procedures. By comparing with some existing marginal screening methods, we show the advantages of the proposed procedures through simulation studies and a real data analysis. Our procedures are model-free and robust against model misspecification, especially useful, when the active predictors are marginally independent of the response.

報告人:鄭石橋      教授    博導

時  間:2018-11-21    14:30

地  點:競慧東樓302

舉辦單位:統計與數學學院  統計科學與大數據研究院