文章基本信息

标题：Case deletion diagnostics in Liu semiparametric regression models
本地全文：下载
作者：Hadi Emami
期刊名称：Journal of Data Science
印刷版ISSN：1680-743X
电子版ISSN：1683-8602
出版年度：2017
卷号：15
期号：2
页码：275-292
出版社：Tingmao Publish Company
摘要：In semiparametric regression it is of interest to detectanomalous observations that exert an unduly large influence on theparameter’s esti-mate and fitted values. Usually the existence ofinfluential observations is complicated by the presence of collinearity.However no method of influ-ence diagnostics available for the possibleeffects that collinearity can have on the influence of an observation on theestimates of parametric and non-parametric component of semiparametricregression models. In this paper we show when Liu estimators are used tomitigate the effects of collinearity the influence of some observations canbe drastically modified. We propose a case deletion formula to detectinfluential points in Liu estimators of semi-parametric regression models .As an illustrative example a real data set are analysed.
关键词：Bandwidth; Cross validation; Diagnostics; Leverages; Liu;esti-mator.