Browsing by Author "Lin, FH"

Now showing 1 - 2 of 2

Generalized cross-validation for wavelet shrinkage in nonparametric mixed effects models
(2003-09-01)
Lu, HHS
;
Huang, SY
;
Lin, FH
;
統計學研究所
;
Institute of Statistics
A nonlinear wavelet shrinkage estimator was proposed in an earlier article by Huang and Lu. Such an estimator combined the asymptotic equivalence to the best linear unbiased prediction and the Bayesian estimation in nonparametric mixed-effects models. In this article, a data-driven GCV method is proposed to select hyperparameters. The proposed GCV method has low computational cost and can be applied to one or higher dimensional data. It can be used for selecting hyperparameters for either level independent or level dependent shrinkage. It can also be used for selecting the primary resolution level and the number of vanishing moments in the wavelet basis. The strong consistency of the GCV method is proved.
Structure importance of consecutive-k-out-of-n systems
(1999-09-01)
Lin, FH
;
Kuo, W
;
Hwang, F
;
應用數學系
;
Department of Applied Mathematics
A consecutive-k-out-of-n : F system is an n-component system that fails when k consecutive components fail. The structure importance is a measure, which indicates the importance of a component relative to its positioning in the system. Through the relationship to the Fibonacci sequence with order k, a closed-form solution of structure importance for each component is obtained. We obtain a complete ordering of the components with respect to their structure importance for some consecutive-k-out-of-n : F systems, and a partial ordering for other systems. (C) 1999 Elsevier Science B.V. All rights reserved.