Laurent, Géraldine ; Université de Liège - ULiège > HEC-Ecole de gestion : UER > UER Opérations
Heuchenne, Cédric ; Université de Liège - ULiège > HEC-Ecole de gestion : UER > Statistique appliquée à la gestion et à l'économie
Language :
English
Title :
Error distribution function for parametrically truncated and censored data
Publication date :
14 September 2012
Event name :
6th Annual Doctoral Workshop of the Graduate School in Statistics and Actuarial Sciences
Event organizer :
UCL
Event place :
Louvain-la-Neuve, Belgium
Event date :
Friday, September 14, 2012
References of the abstract :
Suppose the random vector (X,Y) verifies the nonparametric regression model
Y=m(X)+sigma(X)*epsilon where m(X)=E[Y|X] and sigma²(X)=Var[Y|X] are unknown
smooth functions and the error epsilon, with unknown distribution, is independent of the
covariate X. The pair (X,Y) is obtained from cross-sectional sampling and the response is
subject to random censoring. We define a new estimator for the cumulative distribution
function of the error, where the estimators of m(.) and sigma²(.) are obtained by extending
the conditional estimation methods introduced in de Uña-Alvarez and Iglesias-Perez (2010).
Asymptotic properties of the proposed estimator are established. The performance of the
estimator is investigated through simulations. This estimator is applied to two real-data
problems.
