摘要

In this study, we propose a delete-2 jackknife-after-bootstrap method to refine the cut-offs for the well-known diagnostic measure Cook%26apos;s distance when the data have multiple influential data points with masking and swamping effects. The performance of the proposed method is compared with one of the most recent approaches in the literature through real world examples as well as a designed simulation study.

  • 出版日期2014-11