Estimation of parameters of finite population L-statistics

We consider the estimation of important parameters of a linear combination of order statistics (L-statistic) in a finite population, emphasizing the influence of auxiliary information on the estimation accuracy. Assuming that values of an auxiliary variable are available for all population units, we...

Full description

Bibliographic Details
Main Authors: Dalius Pumputis, Andrius Čiginas
Format: Article
Language:English
Published: Vilnius University Press 2013-07-01
Series:Nonlinear Analysis
Subjects:
Online Access:http://www.journals.vu.lt/nonlinear-analysis/article/view/14013
_version_ 1818368248896290816
author Dalius Pumputis
Andrius Čiginas
author_facet Dalius Pumputis
Andrius Čiginas
author_sort Dalius Pumputis
collection DOAJ
description We consider the estimation of important parameters of a linear combination of order statistics (L-statistic) in a finite population, emphasizing the influence of auxiliary information on the estimation accuracy. Assuming that values of an auxiliary variable are available for all population units, we construct calibrated estimators for the variance of L-statistics and for the parameters, which define one-term Edgeworth expansions of distributions of L-statistics. The gain of the new estimators is demonstrated by the simulation study.
first_indexed 2024-12-13T23:04:56Z
format Article
id doaj.art-2787e8141d924f2893aa94d77199c269
institution Directory Open Access Journal
issn 1392-5113
2335-8963
language English
last_indexed 2024-12-13T23:04:56Z
publishDate 2013-07-01
publisher Vilnius University Press
record_format Article
series Nonlinear Analysis
spelling doaj.art-2787e8141d924f2893aa94d77199c2692022-12-21T23:28:18ZengVilnius University PressNonlinear Analysis1392-51132335-89632013-07-01183Estimation of parameters of finite population L-statisticsDalius Pumputis0Andrius Čiginas1Lithuanian University of Educational Sciences, LithuaniaVilnius University, LithuaniaWe consider the estimation of important parameters of a linear combination of order statistics (L-statistic) in a finite population, emphasizing the influence of auxiliary information on the estimation accuracy. Assuming that values of an auxiliary variable are available for all population units, we construct calibrated estimators for the variance of L-statistics and for the parameters, which define one-term Edgeworth expansions of distributions of L-statistics. The gain of the new estimators is demonstrated by the simulation study.http://www.journals.vu.lt/nonlinear-analysis/article/view/14013finite populationL-statisticvarianceEdgeworth expansionbootstrapcalibration
spellingShingle Dalius Pumputis
Andrius Čiginas
Estimation of parameters of finite population L-statistics
Nonlinear Analysis
finite population
L-statistic
variance
Edgeworth expansion
bootstrap
calibration
title Estimation of parameters of finite population L-statistics
title_full Estimation of parameters of finite population L-statistics
title_fullStr Estimation of parameters of finite population L-statistics
title_full_unstemmed Estimation of parameters of finite population L-statistics
title_short Estimation of parameters of finite population L-statistics
title_sort estimation of parameters of finite population l statistics
topic finite population
L-statistic
variance
Edgeworth expansion
bootstrap
calibration
url http://www.journals.vu.lt/nonlinear-analysis/article/view/14013
work_keys_str_mv AT daliuspumputis estimationofparametersoffinitepopulationlstatistics
AT andriusciginas estimationofparametersoffinitepopulationlstatistics