Sparse Bayesian Variable Selection in Classification Problems with Large p Small n

  • 陳 彥龍

Student thesis: Master's Thesis

Abstract

Finite mixture of regression models provide a flexible method of modeling data that arise from a heterogeneous population Within each sub-population the response variable can be explained by a linear regression on the predictor variables If the number of predictor variables is large it is assumed that only a small subset of variables are important for explaining the response variable It is further assumed that for different subpopulations different subsets of variables may be needed to explain the response variable An Reversible jump MCMC method is proposed to the variable selection procedure that accounts not only for identifying the important variables in each subpopulation but also for determining the number of components in the finite mixture of regression models
Date of Award2016 Jul 7
Original languageEnglish
SupervisorKuo-Jung Lee (Supervisor)

Cite this

'