Jackknife-After-Bootstrap Method for Detection of Influential Observations in Linear Regression Models


Beyaztas U., Alin A.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, vol.42, no.6, pp.1256-1267, 2013 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 42 Issue: 6
  • Publication Date: 2013
  • Doi Number: 10.1080/03610918.2012.661908
  • Title of Journal : COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Page Numbers: pp.1256-1267

Abstract

The jackknife-after-bootstrap (JaB) method has been proposed for detecting influential observations in linear regression models. The performance of JaB and the traditional methods have been compared for four different influence measures by designed simulation study and real world examples. Design includes different sample sizes and various modeling scenarios. The results reveal that proposed method is a good competitor or even better than traditional methods.