Online Program Home
My Program

Abstract Details

Activity Number: 185
Type: Contributed
Date/Time: Monday, August 1, 2016 : 10:30 AM to 12:20 PM
Sponsor: Section on Nonparametric Statistics
Abstract #319391
Title: Optimal Bayes Classifiers for Functional Data and Density Ratios
Author(s): Xiongtao Dai* and Hans-Georg Mueller and Fang Yao
Companies: Healthy Birth, Growth and Development knowledge integration (HBGDki) Community and University of California at Davis and University of Toronto
Keywords: common functional principal component ; density estimation ; functional classification ; Gaussian process ; quadratic discriminant analysis

Bayes classifiers for functional data pose a challenge because probability density functions do not exist for functional data. As a consequence, the classical Bayes classifier using density quotients needs to be modified. We construct Bayes classifiers using density ratios of projections on a sequence of eigenfunctions that are common to the groups to be classified. In the large sample limit, our classifiers have misclassification rate converging to zero under certain conditions, and they also perform favorably in comparisons with other functional classifiers in simulations and various data applications.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association