Optimal parameter estimation of Pareto type model D. N. Politis, V. A. Vasiliev, S. E. Vorobeychikov
Material type:
ArticleOther title: Оптимальное оценивание параметра в модели Парето [Parallel title]Subject(s): распределения с тяжелыми хвостами | Парето распределение | функция риска | усеченная оценка | оптимальный объем выборкиGenre/Form: статьи в сборниках Online resources: Click here to access online
In:
Международная научная конференция "Робастная статистика и финансовая математика - 2018" 09-11 июля 2018 г. : сборник статей С. 48-53Abstract: The general Pareto type model with unknown tail index is
considered. The optimality criterion uses a risk function that
includes a weighted mean square accuracy of tail index estimate
and the sample size. The problem is to find the optimal sample
size to minimize this criterion. It is proposed the asymptotically
optimal (as the coefficient by mean square accuracy of the
estimate tends to infinity) procedure to determine the optimal
sample size. The procedure is based on the truncated estimator
of unknown parameter having optimal convergence rate and uses
a special stopping time. The simulation results are given.
Библиогр.: 3 назв.
The general Pareto type model with unknown tail index is
considered. The optimality criterion uses a risk function that
includes a weighted mean square accuracy of tail index estimate
and the sample size. The problem is to find the optimal sample
size to minimize this criterion. It is proposed the asymptotically
optimal (as the coefficient by mean square accuracy of the
estimate tends to infinity) procedure to determine the optimal
sample size. The procedure is based on the truncated estimator
of unknown parameter having optimal convergence rate and uses
a special stopping time. The simulation results are given.
There are no comments on this title.