Reference : Nonlinear regression with censored data
Scientific journals : Article
Physical, chemical, mathematical & earth Sciences : Mathematics
Nonlinear regression with censored data
Heuchenne, Cédric mailto [Université de Liège - ULiège > HEC - École de gestion de l'ULiège > Statistique appliquée à la gestion et à l'économie >]
Van Keilegom, Ingrid [> > > >]
American Statistical Association
Yes (verified by ORBi)
[en] bootstrap ; fatigue life data ; kernel method ; least squares estimation ; nonparametric regression ; right censoring ; survival analysis ; bandwidth selection
[en] Suppose that the random vector (X, Y) satisfies the regression model Y = m(X) + sigma(X)epsilon, where m(.) = E(Y vertical bar.) belongs to some parametric class (m(theta)(.):theta is an element of Theta) of regression functions, sigma(2)(.) = var(Y vertical bar.) is unknown, and e is independent of X. The response Y is subject to random right censoring, and the covariate X is completely observed. A new estimation procedure for the true, unknown parameter vector theta(0) is proposed that extends the classical least squares procedure for nonlinear regression to the case where the response is subject to censoring. The consistency and asymptotic normality of the proposed estimator are established. The estimator is compared through simulations with an estimator proposed by Stute in 1999, and both methods are also applied to a fatigue life dataset of strain-controlled materials.

File(s) associated to this reference

Fulltext file(s):

Open access
mainart2.pdfPublisher postprint258.16 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.