On the Logistic Regression Diagnostics

  • Kim, Choong-Rak (Department of Statistics, Pusan National University, Pusan, 609-735) ;
  • Jeong, Kwang-Mo (Department of Statistics, Pusan National University, Pusan, 609-735)
  • Published : 1993.06.01

Abstract

Since the analytic expression for a diagnostic in the logistic regression model is not available, one-step estimation is often used by a case-deletion point of view. In this paper, infinitesimal perturbation approach is used, and it is shown that the scale transformation of infinitesimal perturbation approach is eventually equal to the weighted perturbation of local influence approach and the replacement measure. Also, multiple cases deletion for the masking effect is considered.

Keywords

References

  1. Technometrics v.19 Detection of influential observations in linear regression Cook,R.D.
  2. Journal of the Royal Statistical Society, Ser B v.48 Assessment of local influence (with discussion) Cook,R.D.
  3. Biometrika v.34 The estimation from individual records of the relationship between dose and quantal response Finney,D.J.
  4. Unpublished Ph.D. Thesis, Univ. of Wisconsin-Madison A study on influential sets in regression Kim,C.
  5. Local influence and replacement measure (manuscript) Kim,C.
  6. Annals of Statistics v.bf 9 Logistic regression diagnostics Pregibon,D.