Censored Median Regression using Support Vector Machine

• 발행기관: 한국자료분석학회
• 저자명: Jooyong Shim Seong-Eun Ahn
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.6 No.3, 663~670쪽, 전체 8쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2004.06.30

영문 초록

This paper deals with the estimations of the linear and the nonlinear median regressions when the responses are subject to randomly right censoring. The weighted data are formed by redistributing the weights of the censored data to the uncensored data. With the weighted data we propose the estimations of the linear and the nonlinear censored median regressions by the support vector machine. Experimental results are then presented which indicate the performance of the estimation method.

목차

1. Introduction

2. Median Regression using SVM

3. Censored Median Regression using SVM

4. Numerical study

5. Concluding Remarks

References

키워드

Median regression Randomly right censoring Support vector machine