用挥发性模拟数据和经验数据检验时间序列成分(BFTSC)和时间序列成分组(GFTSC)的有效性

Ajare Emmanuel Oloruntoba, Adefabi Adekunle, Adeyemo Abiodun
{"title":"用挥发性模拟数据和经验数据检验时间序列成分(BFTSC)和时间序列成分组(GFTSC)的有效性","authors":"Ajare Emmanuel Oloruntoba, Adefabi Adekunle, Adeyemo Abiodun","doi":"10.9734/ajpas/2023/v24i3527","DOIUrl":null,"url":null,"abstract":"The main reason for this study is to know the performance of BFTSC (Break for Time Series Components) and GFTSC (Group for Time Series Components) in identification of time series components using volatile simulated and empirical data. BFTSC was created to capture the trend, seasonal, cyclical and irregular components and presented them in a time series plot. While GFTSC was designed to capture all the four time series components together with the equations that produces each components of time series. BFAST (Break for Additive, Seasonal and Trend) only identifies trend and seasonal components while considering all other left over components as random, identification of trend and seasonal components alone is not enough to have a clear image of all the time series components in a time series data. Performance through evaluation using low and high volatile simulated and empirical data was conducted to evaluate the performance of both techniques. For yearly sample size of 8, 16 and 24 years were for small medium and large sample size. For the monthly data, 48, 96 and 144 months were used as small, medium and large sample size. Each of the sample size was replicated 100 times each. Finally, GFTSC and BFTSC performance was very good for large sample size with linear trend for both monthly and yearly data (approximately 100%). While the performance drops with highly volatile data such as trend with curve trend line (such as quadratic and cubic). These findings indicate that BFTSC and GFTSC can provide a better alternative to manual technique and BFAST for data associated with linear trend, hence BFTSC and GFTSC are recommended for public.","PeriodicalId":8532,"journal":{"name":"Asian Journal of Probability and Statistics","volume":"113 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Examining the Efficacy of Break for Time Series Components (BFTSC) and Group for Time Series Components (GFTSC) with Volatile Simulated and Empirical Data\",\"authors\":\"Ajare Emmanuel Oloruntoba, Adefabi Adekunle, Adeyemo Abiodun\",\"doi\":\"10.9734/ajpas/2023/v24i3527\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The main reason for this study is to know the performance of BFTSC (Break for Time Series Components) and GFTSC (Group for Time Series Components) in identification of time series components using volatile simulated and empirical data. BFTSC was created to capture the trend, seasonal, cyclical and irregular components and presented them in a time series plot. While GFTSC was designed to capture all the four time series components together with the equations that produces each components of time series. BFAST (Break for Additive, Seasonal and Trend) only identifies trend and seasonal components while considering all other left over components as random, identification of trend and seasonal components alone is not enough to have a clear image of all the time series components in a time series data. Performance through evaluation using low and high volatile simulated and empirical data was conducted to evaluate the performance of both techniques. For yearly sample size of 8, 16 and 24 years were for small medium and large sample size. For the monthly data, 48, 96 and 144 months were used as small, medium and large sample size. Each of the sample size was replicated 100 times each. Finally, GFTSC and BFTSC performance was very good for large sample size with linear trend for both monthly and yearly data (approximately 100%). While the performance drops with highly volatile data such as trend with curve trend line (such as quadratic and cubic). These findings indicate that BFTSC and GFTSC can provide a better alternative to manual technique and BFAST for data associated with linear trend, hence BFTSC and GFTSC are recommended for public.\",\"PeriodicalId\":8532,\"journal\":{\"name\":\"Asian Journal of Probability and Statistics\",\"volume\":\"113 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Asian Journal of Probability and Statistics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.9734/ajpas/2023/v24i3527\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Asian Journal of Probability and Statistics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.9734/ajpas/2023/v24i3527","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本研究的主要原因是了解BFTSC (Break for Time Series Components)和GFTSC (Group for Time Series Components)在使用挥发性模拟数据和经验数据识别时间序列成分方面的性能。创建BFTSC是为了捕捉趋势、季节性、周期性和不规则成分,并将它们呈现在时间序列图中。而GFTSC的设计是为了捕捉所有的四个时间序列组成部分以及产生时间序列的每个组成部分的方程。BFAST (Break for Additive, Seasonal and Trend)只识别趋势和季节分量,而考虑到其他所有剩余分量都是随机的,仅识别趋势和季节分量不足以清晰地显示时间序列数据中的所有时间序列分量。通过使用低挥发性和高挥发性模拟数据和经验数据对两种技术的性能进行了评估。年样本量为8年,16年和24年为中小样本量和大样本量。月度数据采用小样本量、中样本量和大样本量分别为48、96和144个月。每个样本量都被重复了100次。最后,GFTSC和BFTSC在大样本量下表现良好,月度和年度数据均呈线性趋势(约100%)。而对于具有曲线趋势线(如二次曲线和三次曲线)的高波动性数据,性能下降。这些结果表明BFTSC和GFTSC可以更好地替代手工技术和BFAST,因此推荐BFTSC和GFTSC用于公众。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Examining the Efficacy of Break for Time Series Components (BFTSC) and Group for Time Series Components (GFTSC) with Volatile Simulated and Empirical Data
The main reason for this study is to know the performance of BFTSC (Break for Time Series Components) and GFTSC (Group for Time Series Components) in identification of time series components using volatile simulated and empirical data. BFTSC was created to capture the trend, seasonal, cyclical and irregular components and presented them in a time series plot. While GFTSC was designed to capture all the four time series components together with the equations that produces each components of time series. BFAST (Break for Additive, Seasonal and Trend) only identifies trend and seasonal components while considering all other left over components as random, identification of trend and seasonal components alone is not enough to have a clear image of all the time series components in a time series data. Performance through evaluation using low and high volatile simulated and empirical data was conducted to evaluate the performance of both techniques. For yearly sample size of 8, 16 and 24 years were for small medium and large sample size. For the monthly data, 48, 96 and 144 months were used as small, medium and large sample size. Each of the sample size was replicated 100 times each. Finally, GFTSC and BFTSC performance was very good for large sample size with linear trend for both monthly and yearly data (approximately 100%). While the performance drops with highly volatile data such as trend with curve trend line (such as quadratic and cubic). These findings indicate that BFTSC and GFTSC can provide a better alternative to manual technique and BFAST for data associated with linear trend, hence BFTSC and GFTSC are recommended for public.
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
自引率
0.00%
发文量
0
期刊最新文献
Bayesian Sequential Updation and Prediction of Currency in Circulation Using a Weighted Prior Assessment of Required Sample Sizes for Estimating Proportions Rainfall Pattern in Kenya: Bayesian Non-parametric Model Based on the Normalized Generalized Gamma Process Advancing Retail Predictions: Integrating Diverse Machine Learning Models for Accurate Walmart Sales Forecasting Common Fixed-Point Theorem for Expansive Mappings in Dualistic Partial Metric Spaces
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1