The Effectiveness of the Huber's Weight on Dispersion and Tuning Constant: A Simulation Study

IF 0.9 Q3 ECONOMICS

Scientific Annals of Economics and Business Pub Date : 2023-06-20 DOI:10.47743/saeb-2023-0022

Intan Martina Md Ghani, Hanafi A Rahim

{"title":"The Effectiveness of the Huber's Weight on Dispersion and Tuning Constant: A Simulation Study","authors":"Intan Martina Md Ghani, Hanafi A Rahim","doi":"10.47743/saeb-2023-0022","DOIUrl":null,"url":null,"abstract":"Dispersion measurement and tuning constants are critical aspects of a model's robustness and efficiency. However, in the presence of outliers, the standard deviation is not a reliable measure of dispersion in Huber's weight. This research aimed to assess the efficacy of the Huber weight function in terms of dispersion measurement and tuning constant. The simulation study was conducted on a hybrid of the autoregressive (AR) model and the generalized autoregressive conditional heteroscedasticity (GARCH) model with 10% and 20% additive outlier contamination. In the simulation analysis, three dispersion measurements were compared: median absolute deviation (MAD), interquartile range (IQR), and IQR/3, with two tuning constant values (1.345 and 1.5). The numerical simulation results showed that during contamination with 10% and 20% additive outliers, the IQR/3 outperformed the MAD and IQR. Our findings also showed that IQR/3 is a potentially more robust dispersion measurement in Huber's weight. The tuning constant of 1.5 revealed a decrease in resistance to outliers and increased efficiency. The proposed IQR/3 model with a constant tuning value (h) of 1.5 outperformed the AR(1)-GARCH(1,2) model while minimising the effect of additive outliers.","PeriodicalId":43189,"journal":{"name":"Scientific Annals of Economics and Business","volume":" ","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scientific Annals of Economics and Business","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.47743/saeb-2023-0022","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ECONOMICS","Score":null,"Total":0}

引用次数: 0

Abstract

Dispersion measurement and tuning constants are critical aspects of a model's robustness and efficiency. However, in the presence of outliers, the standard deviation is not a reliable measure of dispersion in Huber's weight. This research aimed to assess the efficacy of the Huber weight function in terms of dispersion measurement and tuning constant. The simulation study was conducted on a hybrid of the autoregressive (AR) model and the generalized autoregressive conditional heteroscedasticity (GARCH) model with 10% and 20% additive outlier contamination. In the simulation analysis, three dispersion measurements were compared: median absolute deviation (MAD), interquartile range (IQR), and IQR/3, with two tuning constant values (1.345 and 1.5). The numerical simulation results showed that during contamination with 10% and 20% additive outliers, the IQR/3 outperformed the MAD and IQR. Our findings also showed that IQR/3 is a potentially more robust dispersion measurement in Huber's weight. The tuning constant of 1.5 revealed a decrease in resistance to outliers and increased efficiency. The proposed IQR/3 model with a constant tuning value (h) of 1.5 outperformed the AR(1)-GARCH(1,2) model while minimising the effect of additive outliers.

查看原文本刊更多论文

Huber权重对色散和调谐常数影响的仿真研究

色散测量和调谐常数是模型鲁棒性和效率的关键方面。然而，在存在异常值的情况下，标准偏差并不能可靠地衡量Huber权值的离散度。本研究旨在评估Huber权函数在色散测量和调谐常数方面的有效性。模拟研究采用自回归(AR)模型和广义自回归条件异方差(GARCH)模型的混合模型，分别添加10%和20%的离群值污染。在模拟分析中，比较了三个离散度测量值:中位数绝对偏差(MAD)，四分位间距(IQR)和IQR/3，两个调谐常数值(1.345和1.5)。数值模拟结果表明，在添加10%和20%异常值污染时，IQR/3优于MAD和IQR。我们的研究结果还表明，IQR/3是一种潜在的更可靠的Huber体重分散测量方法。调整常数为1.5表明对异常值的抵抗力降低，效率提高。所提出的IQR/3模型具有恒定的调谐值(h)为1.5，其性能优于AR(1)-GARCH(1,2)模型，同时最小化了附加异常值的影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Scientific Annals of Economics and Business ECONOMICS-

CiteScore

1.40

自引率

0.00%

发文量

审稿时长

10 weeks

期刊介绍： The Journal called Scientific Annals of Economics and Business (formerly Analele ştiinţifice ale Universităţii "Al.I. Cuza" din Iaşi. Ştiinţe economice / Scientific Annals of the Alexandru Ioan Cuza University of Iasi. Economic Sciences), was first published in 1954. It is published under the care of the Alexandru Ioan Cuza University, the oldest higher education institution in Romania, a place of excellence and innovation in education and research since 1860. Throughout its editorial life, the journal has been continuously improving. Renowned professors, well-known in the country and abroad, have published in this journal. The quality of the published materials is ensured both through their review by external reviewers of the institution and by the editorial staff that includes professors for each area of interest. The journal published papers in the following main sections: Accounting; Finance, Money and Banking; Management, Marketing and Communication; Microeconomics and Macroeconomics; Statistics and Econometrics; The Society of Knowledge and Business Information Systems.