Geodesic
Pareto approximation of the tail by local exponential modeling
Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica, no. 1 (2007), pp. 3-24

Voir la notice de l'article provenant de la source Math-Net.Ru

We give a new adaptive method for selecting the number of upper order statistics used in the estimation of the tail of a distribution function. Our approach is based on approximation by an exponential model. The selection procedure consists in consecutive testing for the hypothesis of homogeneity of the estimated parameter against the change-point alternative. The selected number of upper order statistics corresponds to the first detected change-point. Our main results are non-asymptotic. 
@article{BASM_2007_1_a0,
     author = {Ion Grama and Vladimir Spokoiny},
     title = {Pareto approximation of the tail by local exponential modeling},
     journal = {Buletinul Academiei de \c{S}tiin\c{t}e a Republicii Moldova. Matematica},
     pages = {3--24},
     publisher = {mathdoc},
     number = {1},
     year = {2007},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/BASM_2007_1_a0/}
}
TY  - JOUR
AU  - Ion Grama
AU  - Vladimir Spokoiny
TI  - Pareto approximation of the tail by local exponential modeling
JO  - Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica
PY  - 2007
SP  - 3
EP  - 24
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/BASM_2007_1_a0/
LA  - en
ID  - BASM_2007_1_a0
ER  - 
%0 Journal Article
%A Ion Grama
%A Vladimir Spokoiny
%T Pareto approximation of the tail by local exponential modeling
%J Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica
%D 2007
%P 3-24
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/BASM_2007_1_a0/
%G en
%F BASM_2007_1_a0
Ion Grama; Vladimir Spokoiny. Pareto approximation of the tail by local exponential modeling. Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica, no. 1 (2007), pp. 3-24. http://geodesic.mathdoc.fr/item/BASM_2007_1_a0/