通过改变辅助变量的分布形状来减少偏差和均方误差:应用于泰国南的空气污染数据

IF 1.4 3区社会学 Q3 DEMOGRAPHY

Mathematical Population Studies Pub Date : 2022-12-05 DOI:10.1080/08898480.2022.2145790

Natthapat Thongsak, Nuanpan Lawson

{"title":"通过改变辅助变量的分布形状来减少偏差和均方误差:应用于泰国南的空气污染数据","authors":"Natthapat Thongsak, Nuanpan Lawson","doi":"10.1080/08898480.2022.2145790","DOIUrl":null,"url":null,"abstract":"ABSTRACT The proposed estimator of the population mean is based on a modification of the shape of the distribution of an auxiliary variable. If the theoretical correlation between the study and the auxiliary variables is less than a term that is proportional to the coefficient of variation of the auxiliary variable divided by the coefficient of variation of the study variable, then the modification of the distribution of the auxiliary variable reduces the bias and the mean square error of the estimator. A simulation confirms the analytical results. Application to air pollution data in Nan, Thailand, shows that on average, the biases of the estimators based on the modified auxiliary variable are reduced by 70% to 98% and the mean square errors by 91% to 100% compared to the estimators based on the unmodified auxiliary variable.","PeriodicalId":49859,"journal":{"name":"Mathematical Population Studies","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Bias and mean square error reduction by changing the shape of the distribution of an auxiliary variable: application to air pollution data in Nan, Thailand\",\"authors\":\"Natthapat Thongsak, Nuanpan Lawson\",\"doi\":\"10.1080/08898480.2022.2145790\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT The proposed estimator of the population mean is based on a modification of the shape of the distribution of an auxiliary variable. If the theoretical correlation between the study and the auxiliary variables is less than a term that is proportional to the coefficient of variation of the auxiliary variable divided by the coefficient of variation of the study variable, then the modification of the distribution of the auxiliary variable reduces the bias and the mean square error of the estimator. A simulation confirms the analytical results. Application to air pollution data in Nan, Thailand, shows that on average, the biases of the estimators based on the modified auxiliary variable are reduced by 70% to 98% and the mean square errors by 91% to 100% compared to the estimators based on the unmodified auxiliary variable.\",\"PeriodicalId\":49859,\"journal\":{\"name\":\"Mathematical Population Studies\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2022-12-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Mathematical Population Studies\",\"FirstCategoryId\":\"90\",\"ListUrlMain\":\"https://doi.org/10.1080/08898480.2022.2145790\",\"RegionNum\":3,\"RegionCategory\":\"社会学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"DEMOGRAPHY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mathematical Population Studies","FirstCategoryId":"90","ListUrlMain":"https://doi.org/10.1080/08898480.2022.2145790","RegionNum":3,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"DEMOGRAPHY","Score":null,"Total":0}

引用次数: 2

摘要

提出的总体均值估计量是基于对辅助变量分布形状的修改。如果研究与辅助变量之间的理论相关性小于与辅助变量的变异系数除以研究变量的变异系数成正比的一项，则对辅助变量分布的修改可以减小估计器的偏置和均方误差。仿真验证了分析结果。对泰国南空气污染数据的应用表明，平均而言，与基于未修改辅助变量的估计器相比，基于修改辅助变量的估计器的偏差减少了70%至98%，均方误差减少了91%至100%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Bias and mean square error reduction by changing the shape of the distribution of an auxiliary variable: application to air pollution data in Nan, Thailand

ABSTRACT The proposed estimator of the population mean is based on a modification of the shape of the distribution of an auxiliary variable. If the theoretical correlation between the study and the auxiliary variables is less than a term that is proportional to the coefficient of variation of the auxiliary variable divided by the coefficient of variation of the study variable, then the modification of the distribution of the auxiliary variable reduces the bias and the mean square error of the estimator. A simulation confirms the analytical results. Application to air pollution data in Nan, Thailand, shows that on average, the biases of the estimators based on the modified auxiliary variable are reduced by 70% to 98% and the mean square errors by 91% to 100% compared to the estimators based on the unmodified auxiliary variable.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Mathematical Population Studies 数学-数学跨学科应用

CiteScore

3.20

自引率

11.10%

发文量

审稿时长

>12 weeks

期刊介绍： Mathematical Population Studies publishes carefully selected research papers in the mathematical and statistical study of populations. The journal is strongly interdisciplinary and invites contributions by mathematicians, demographers, (bio)statisticians, sociologists, economists, biologists, epidemiologists, actuaries, geographers, and others who are interested in the mathematical formulation of population-related questions. The scope covers both theoretical and empirical work. Manuscripts should be sent to Manuscript central for review. The editor-in-chief has final say on the suitability for publication.