Asymptotics for Configural Estimators.
Abstract
This paper examines the asymptotic properties of compromise estimators. By this we mean an estimation method which compromises between a finite number of sampling situations in a small sample optimal way. We develop the asymptotic theory of such estimators and show that under a specific choice of sampling situations the compromise estimator is asymptotically robust in Huber's sense. Originator-supplied keywords include: Robust estimation, Conditional inference, Equivariance, Asymptotics.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1984
- Accession Number
- ADA150106
Entities
People
- S. Morgenthaler
Organizations
- Massachusetts Institute of Technology