UNIGE document Scientific Article
previous document  unige:75150  next document
add to browser collection
Title

On robust estimation via pseudo-additive information

Authors
Ferrari, Davide
Published in Biometrika. 2012, vol. 99, no. 1, p. 238-244
Abstract We consider a robust parameter estimator minimizing an empirical approximation to the q-entropy and show its relationship to minimization of power divergences through a simple parameter transformation. The estimator balances robustness and efficiency through a tuning constant q and avoids kernel density smoothing. We derive an upper bound to the estimator mean squared error under a contaminated reference model and use it as a min-max criterion for selecting q.
Keywords Change-of-varianceMinimum divergence estimationPower divergenceQ-entropyRobustness
Identifiers
Full text
Article (Published version) (128 Kb) - document accessible for UNIGE members only Limited access to UNIGE
Article (Author postprint) (135 Kb) - document accessible for UNIGE members only Limited access to UNIGE
Other version: http://biomet.oxfordjournals.org/content/99/1/238.full.pdf
Structures
Citation
(ISO format)
LA VECCHIA, Davide, FERRARI, Davide. On robust estimation via pseudo-additive information. In: Biometrika, 2012, vol. 99, n° 1, p. 238-244. https://archive-ouverte.unige.ch/unige:75150

132 hits

0 download

Update

Deposited on : 2015-09-13

Export document
Format :
Citation style :