Consistency and robustness of Cramér-von Mises type estimators

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F11%3A00184131" target="_blank" >RIV/68407700:21340/11:00184131 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Consistency and robustness of Cramér-von Mises type estimators
Original language description
The paper focuses on the minimum distance density estimates of a probability density function on the real line. We introduce new generalization of Cramér-von Mises distance estimate and so called Kolmogorov-Cramér minimum distance estimate (KC) which includes both Kolmogorov and Cramér-von Mises estimates as the limiting special cases. We prove the consistency of KC estimates in the L1-norm by direct technique employing uniform and local domination relations between statistical distances. Further, we study robustness of this two newly defined estimates and their efficiency for non-contaminated and contaminated samples. Computer simulations compare properties of the minimum Kolmogorov, Cramér-von Mises, Kolmogorov-Cramér, and generalized Cramér-von Mises distance estimates as for the quality of consistency and robustness.
Czech name
—
Czech description
—

Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 17th European Young Statisticians Meeting
ISBN
978-972-8893-27-9
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
99-103
Publisher name
Univesidade Nova de Lisboa - Faculdade de ciencias e technologia
Place of publication
Lisabon
Event location
Lisbon
Event date
Sep 5, 2011
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)