Optimally hounded score functions for generalized linear models with applications to logistic regression Academic Article uri icon

abstract

  • We study optimally bounded score functions for estimating regression parameters in a generalized linear model. Our work extends results obtained by Krasker & Welsch (1982) for the linear model and provides a simple proof of Krasker & Welsch's first-order condition for strong optimality. The application of these results to logistic regression is studied in some detail with an example given comparing the bounded-influence estimator with maximum likelihood. 1986 Biometrika Trust.

published proceedings

  • Biometrika

author list (cited authors)

  • STEFANSKI, L. A., CARROLL, R. J., & RUPPERT, D.

citation count

  • 41

complete list of authors

  • STEFANSKI, LEONARD A||CARROLL, RAYMOND J||RUPPERT, DAVID

publication date

  • August 1986