Kernel Ridge Regression with Randomly Right Censored Data
Kernel Ridge Regression with Randomly Right Censored Data
- 한국통계학회
- Communications for Statistical Applications and Methods
- 15(2)
-
2008.03205 - 212 (8 pages)
- 0
This paper deals with the estimations of kernel ridge regression when the re-sponses are subject to randomly right censoring. The iterative reweighted leastsquares(IRWLS) procedure is employed to treat censored observations. The hyper-parameters of model which aect the performance of the proposed procedure areselected by a generalized cross validation(GCV) function. Experimental results arethen presented which indicate the performance of the proposed procedure.
This paper deals with the estimations of kernel ridge regression when the re-sponses are subject to randomly right censoring. The iterative reweighted leastsquares(IRWLS) procedure is employed to treat censored observations. The hyper-parameters of model which aect the performance of the proposed procedure areselected by a generalized cross validation(GCV) function. Experimental results arethen presented which indicate the performance of the proposed procedure.
(0)
(0)