Incorporating auxiliary information for improved prediction using combination of kernel machines

Xiang Zhan, Debashis Ghosh

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

With evolving genomic technologies, it is possible to get different measures of the same underlying biological phenomenon using different technologies. The goal of this paper is to build a prediction model for an outcome variable Y from covariates X. Besides X, we have surrogate covariates W which are related to X. We want to utilize the information in W to boost the prediction for Y using X. In this paper, we propose a kernel machine-based method to improve prediction of Y by X by incorporating auxiliary information W. By combining single kernel machines, we also propose a hybrid kernel machine predictor, which can yield a smaller prediction error than its constituents. The prediction error of our kernel machine predictors is evaluated using simulations. We also apply our method to a lung cancer dataset and an Alzheimer's disease dataset.

Original languageEnglish (US)
Pages (from-to)47-57
Number of pages11
JournalStatistical Methodology
Volume22
DOIs
StatePublished - Jan 1 2015

Fingerprint

Kernel Machines
Auxiliary Information
Prediction
Prediction Error
Covariates
Predictors
Alzheimer's Disease
Lung Cancer
Prediction Model
Genomics
Simulation

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

Cite this

@article{d0bb9f90887d400ca433847205b2444b,
title = "Incorporating auxiliary information for improved prediction using combination of kernel machines",
abstract = "With evolving genomic technologies, it is possible to get different measures of the same underlying biological phenomenon using different technologies. The goal of this paper is to build a prediction model for an outcome variable Y from covariates X. Besides X, we have surrogate covariates W which are related to X. We want to utilize the information in W to boost the prediction for Y using X. In this paper, we propose a kernel machine-based method to improve prediction of Y by X by incorporating auxiliary information W. By combining single kernel machines, we also propose a hybrid kernel machine predictor, which can yield a smaller prediction error than its constituents. The prediction error of our kernel machine predictors is evaluated using simulations. We also apply our method to a lung cancer dataset and an Alzheimer's disease dataset.",
author = "Xiang Zhan and Debashis Ghosh",
year = "2015",
month = "1",
day = "1",
doi = "10.1016/j.stamet.2014.08.001",
language = "English (US)",
volume = "22",
pages = "47--57",
journal = "Statistical Methodology",
issn = "1572-3127",
publisher = "Elsevier",

}

Incorporating auxiliary information for improved prediction using combination of kernel machines. / Zhan, Xiang; Ghosh, Debashis.

In: Statistical Methodology, Vol. 22, 01.01.2015, p. 47-57.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Incorporating auxiliary information for improved prediction using combination of kernel machines

AU - Zhan, Xiang

AU - Ghosh, Debashis

PY - 2015/1/1

Y1 - 2015/1/1

N2 - With evolving genomic technologies, it is possible to get different measures of the same underlying biological phenomenon using different technologies. The goal of this paper is to build a prediction model for an outcome variable Y from covariates X. Besides X, we have surrogate covariates W which are related to X. We want to utilize the information in W to boost the prediction for Y using X. In this paper, we propose a kernel machine-based method to improve prediction of Y by X by incorporating auxiliary information W. By combining single kernel machines, we also propose a hybrid kernel machine predictor, which can yield a smaller prediction error than its constituents. The prediction error of our kernel machine predictors is evaluated using simulations. We also apply our method to a lung cancer dataset and an Alzheimer's disease dataset.

AB - With evolving genomic technologies, it is possible to get different measures of the same underlying biological phenomenon using different technologies. The goal of this paper is to build a prediction model for an outcome variable Y from covariates X. Besides X, we have surrogate covariates W which are related to X. We want to utilize the information in W to boost the prediction for Y using X. In this paper, we propose a kernel machine-based method to improve prediction of Y by X by incorporating auxiliary information W. By combining single kernel machines, we also propose a hybrid kernel machine predictor, which can yield a smaller prediction error than its constituents. The prediction error of our kernel machine predictors is evaluated using simulations. We also apply our method to a lung cancer dataset and an Alzheimer's disease dataset.

UR - http://www.scopus.com/inward/record.url?scp=84908095492&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908095492&partnerID=8YFLogxK

U2 - 10.1016/j.stamet.2014.08.001

DO - 10.1016/j.stamet.2014.08.001

M3 - Article

VL - 22

SP - 47

EP - 57

JO - Statistical Methodology

JF - Statistical Methodology

SN - 1572-3127

ER -