|
|||||
|
|
The breakdown behavior of the maximum likelihood estimator in the logistic regression model |
|
| Authors: | Christophe Croux Ccile Flandre Gentiane Haesbroeck |
| Institution: | a Department of Applied Economics, Katholieke Universiteit Leuven, Naamsestraat 69, B-3000, Leuven, Belgium b Cardif Vie S.A., Chaussée de la Hulpe 150, B-1170, Bruxelles, Belgium c Department of Mathematics, University of Liège (B37), Grande Traverse 12, B-4000, Liège, Belgium |
| Abstract: | In this note we discuss the breakdown behavior of the maximum likelihood (ML) estimator in the logistic regression model. We formally prove that the ML-estimator never explodes to infinity, but rather breaks down to zero when adding severe outliers to a data set. An example confirms this behavior. |
| Keywords: | Breakdown point Logistic regression Maximum likelihood Robust estimation |
| 本文献已被 ScienceDirect 等数据库收录！ | |