ON A SIMPLE ESTIMATION PROCEDURE FOR CENSORED REGRESSION-MODELS WITH KNOWN ERROR DISTRIBUTIONS

Authors
BREIMAN L TSUR Y ZEMEL A
Citation
L. Breiman et al., ON A SIMPLE ESTIMATION PROCEDURE FOR CENSORED REGRESSION-MODELS WITH KNOWN ERROR DISTRIBUTIONS, Annals of statistics, 21(4), 1993, pp. 1711-1720
Citations number
12
Categorie Soggetti
Statistic & Probability","Statistic & Probability
Journal title
Annals of statistics → ACNP
ISSN journal
00905364
Volume
21
Issue
4
Year of publication
1993
Pages
1711 - 1720
Database
ISI
SICI code
0090-5364(1993)21:4<1711:OASEPF>2.0.ZU;2-X
Abstract
A simple and tractable iterative least squares estimation procedure fo r censored regression models with known error distributions is analyze d. It is found to be equivalent to a well-defined Huber type M-estimat e. Under a regularity condition, the algorithm converges geometrically to a unique solution. The resulting estimate is square-root N-consist ent and asymptotically normal.