Cover Image

Simulations on the Theil-Sen regression estimator with right-censored data

This note compares the small-sample efficiency of the extended Theil-Sen estimator to the modified Buckley-James estimator when the predictor is random. Included are situations where the error term is heteroscedastic. In terms of their standard errors, the extended Theil-Sen estimator is found to offer a substantial advantage in various situations, while the modified Buckley-James estimator never offers an advantage when there is 20% or 50% censoring.
Year of publication:
1998
Authors: Wilcox, Rand R.
Published in:
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 39.1998, 1, p. 43-47
Publisher: Elsevier
Subject: Buckley-James estimator Bootstrap
Online Resource
Check full text access |
Check Google Scholar
In libraries world-wide (WorldCat)
In German libraries (KVK)
subito order
I need help
Type of publication: Article
Source:
Persistent link: https://www.econbiz.de/10005223224
Similar items by person