UNIGE document Scientific Article
previous document  unige:23354  next document
add to browser collection

Robust Estimation for Grouped Data

Published in Journal of the American Statistical Association. 1997, vol. 92, no. 437, p. 333-340
Abstract Here we investigate the robustness properties of the class of minimum power divergence estimators for grouped data. This class contains the classical maximum likelihood estimators for grouped data. We find that the bias of these estimators due to deviations from the assumed underlying model can be large. Therefore, we propose a more general class of estimators that allows us to construct robust procedures. By analogy with Hampel's theorem, we define optimal bounded influence function estimators, and by a simulation study, we show that under small model contaminations, these estimators are more stable than the classical estimators for grouped data. Finally, we apply our results to a particular real example.
Keywords DiagnosticsGrouping effectsInfluence functionLocal shift sensitivityM estimatorsMinimum Hellinger distance estimatorsMinimum power divergence estimatorsOptimal B-robust estimators
Full text
(ISO format)
VICTORIA-FESER, Maria-Pia, RONCHETTI, Elvezio. Robust Estimation for Grouped Data. In: Journal of the American Statistical Association, 1997, vol. 92, n° 437, p. 333-340. https://archive-ouverte.unige.ch/unige:23354

147 hits

0 download


Deposited on : 2012-10-16

Export document
Format :
Citation style :