Conditionally Unbiased Bounded Influence Robust Regression with Applications to Generalized Linear Models.
Abstract
This document proposes a class of bounded influence robust regression estimators with conditionally unbiased estimating functions given the design. Optimal estimators are found within this class. Applications are made to generalized linear models. An example applying logistic regression to food stamp data is discussed. Keywords: Asymptotic bias; Generalized linear models; Linear regression.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1987
- Accession Number
- ADA186319
Entities
People
- H. R. Kunsch
- L. A. Stefanski
- Raymond J. Carroll
Organizations
- University of North Carolina at Chapel Hill