JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 18
Type: Topic Contributed
Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
Sponsor: International Chinese Statistical Association
Abstract #315271 View Presentation
Title: Support Vector Classification with Missing Covariates
Author(s): Michael C. Wu* and Thomas G. Stewart and Donglin Zeng
Companies: Fred Hutchinson Cancer Research Center and The University of North Carolina at Chapel Hill and The University of North Carolina
Keywords: classification ; fisher consistency ; missing data ; kernel machines ; support vector machines
Abstract:

Support vector machines (SVM) have demonstrated utility for a wide variety of classification tasks. A key feature of SVMs is that they allow for construction of both linear and non-linear decision rules which can yield better prediction when the data are complex, as is frequently the case in biomedical studies. A practical challenge for SVMs, as with many other classification methods, lies in the accommodation of missing data which commonly occur in real data applications due to imperfect data collection. Currently, many researchers rely on complete-case or imputation solutions which may introduce bias and lead to reduced classification accuracy. Therefore, we propose an EM-motivated solution to the incomplete data problem for SVMs which maintains the convex objective function and which allows the researcher to use the same software as the complete case solution. Simulations show that the proposed method often yields classification rules with higher accuracy than existing methods. We apply the approach to analyze data from HCV-TARGET, a longitudinal study of Hepatitis C patients.


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

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home