Measures of the sensitivity of regression estimates to the choice of estimator

• 成果类型: Article
• 署名作者: Severini, TA
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.2307/2291592
• 发表日期: 1996
• 页码: 1651-1658
• 关键词: likelihood inference; quantiles; location; models

摘要

Let Y-1,...,Y-n denote independent real-valued observations, each of the form Y-j = X(j) beta + sigma epsilon(j), where X(j) is a fixed covariate vector, beta and sigma are unknown parameters, and epsilon(1),...,epsilon(n) are identically distributed according to a symmetric density p. This article considers the sensitivity of point estimates of beta to the choice of estimator from classes of estimators based on the L estimators of Kroenker and Portnoy. Specific measures of sensitivity are proposed, and these measures are applied to several datasets.