Investigation of Accuracy of a Calibrated Estimator of a Ratio by Modelling
Articles
V. Chadyšas
Vilnius Gediminas Technical University, Lithuania
D. Krapavickaitė
Vilnius Gediminas Technical University; Institute of Mathematics and Informatics, Lithuania
Published 2005-10-25
https://doi.org/10.15388/NA.2005.10.4.15113
PDF

Keywords

finite population
ratio of two totals
simple random sampling
calibrated estimator

How to Cite

Chadyšas, V. and Krapavickaitė, D. (2005) “Investigation of Accuracy of a Calibrated Estimator of a Ratio by Modelling”, Nonlinear Analysis: Modelling and Control, 10(4), pp. 333–342. doi:10.15388/NA.2005.10.4.15113.

Abstract

Estimator of finite population parameter – ratio of totals of two variables – is investigated by modelling in the case of simple random sampling. Traditional estimator of the ratio is compared with the calibrated estimator of the ratio introduced by Plikusas [1]. The Taylor series expansion of the estimators are used for the expressions of approximate biases and approximate variances [2]. Some estimator of bias is introduced in this paper. Using data of artificial population the accuracy of two estimators of the ratio is compared by modelling. Dependence of the estimates of mean square error of the estimators of the ratio on the correlation coefficient of variables which are used in the numerator and denominator, is also shown in the modelling.

PDF

Downloads

Download data is not yet available.