具有季节和空间变化的气候数据的非参数面板模型

IF 1.5 3区数学 Q2 SOCIAL SCIENCES, MATHEMATICAL METHODS

Journal of the Royal Statistical Society Series A-Statistics in Society Pub Date : 2023-08-03 DOI:10.1093/jrsssa/qnad086

Jiti Gao, O. Linton, B. Peng

{"title":"具有季节和空间变化的气候数据的非参数面板模型","authors":"Jiti Gao, O. Linton, B. Peng","doi":"10.1093/jrsssa/qnad086","DOIUrl":null,"url":null,"abstract":"\n We consider a panel data model that allows for heterogeneous time trends at different locations. The model is well suited to identifying trends in climate data recorded at multiple stations. We propose a new estimation method for the model and derive an asymptotic theory for the proposed estimation method. For inferential purposes, we develop a bootstrap method for the case where weak correlation presents in both dimensions of the error terms. We examine the finite-sample properties of the proposed model and estimation method through extensive simulated studies. Finally, we use the newly proposed model and method to investigate monthly rainfall, temperature, and sunshine data of the UK, respectively. Overall, we find spring and winter have changed significantly over the past 50 years. Changes vary with respect to locations for the other seasons.","PeriodicalId":49983,"journal":{"name":"Journal of the Royal Statistical Society Series A-Statistics in Society","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A non-parametric panel model for climate data with seasonal and spatial variation\",\"authors\":\"Jiti Gao, O. Linton, B. Peng\",\"doi\":\"10.1093/jrsssa/qnad086\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n We consider a panel data model that allows for heterogeneous time trends at different locations. The model is well suited to identifying trends in climate data recorded at multiple stations. We propose a new estimation method for the model and derive an asymptotic theory for the proposed estimation method. For inferential purposes, we develop a bootstrap method for the case where weak correlation presents in both dimensions of the error terms. We examine the finite-sample properties of the proposed model and estimation method through extensive simulated studies. Finally, we use the newly proposed model and method to investigate monthly rainfall, temperature, and sunshine data of the UK, respectively. Overall, we find spring and winter have changed significantly over the past 50 years. Changes vary with respect to locations for the other seasons.\",\"PeriodicalId\":49983,\"journal\":{\"name\":\"Journal of the Royal Statistical Society Series A-Statistics in Society\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2023-08-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of the Royal Statistical Society Series A-Statistics in Society\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://doi.org/10.1093/jrsssa/qnad086\",\"RegionNum\":3,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"SOCIAL SCIENCES, MATHEMATICAL METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Royal Statistical Society Series A-Statistics in Society","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1093/jrsssa/qnad086","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SOCIAL SCIENCES, MATHEMATICAL METHODS","Score":null,"Total":0}

引用次数: 0

摘要

我们考虑了一个面板数据模型，该模型允许不同位置的异构时间趋势。该模式非常适合于识别多个站点记录的气候数据的趋势。我们提出了一种新的模型估计方法，并推导了该估计方法的渐近理论。出于推理的目的，我们开发了一种自举方法，用于在误差项的两个维度上都存在弱相关性的情况。我们通过广泛的模拟研究来检验所提出的模型和估计方法的有限样本性质。最后，我们使用新提出的模型和方法分别调查了英国的月降雨量、温度和日照数据。总的来说，我们发现在过去的50年里，春天和冬天发生了很大的变化。其他季节的变化随地点的不同而不同。

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

A non-parametric panel model for climate data with seasonal and spatial variation

We consider a panel data model that allows for heterogeneous time trends at different locations. The model is well suited to identifying trends in climate data recorded at multiple stations. We propose a new estimation method for the model and derive an asymptotic theory for the proposed estimation method. For inferential purposes, we develop a bootstrap method for the case where weak correlation presents in both dimensions of the error terms. We examine the finite-sample properties of the proposed model and estimation method through extensive simulated studies. Finally, we use the newly proposed model and method to investigate monthly rainfall, temperature, and sunshine data of the UK, respectively. Overall, we find spring and winter have changed significantly over the past 50 years. Changes vary with respect to locations for the other seasons.

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

Journal of the Royal Statistical Society Series A-Statistics in Society 数学-统计学与概率论

CiteScore

2.90

自引率

5.00%

发文量

136

审稿时长

>12 weeks

期刊介绍： Series A (Statistics in Society) publishes high quality papers that demonstrate how statistical thinking, design and analyses play a vital role in all walks of life and benefit society in general. There is no restriction on subject-matter: any interesting, topical and revelatory applications of statistics are welcome. For example, important applications of statistical and related data science methodology in medicine, business and commerce, industry, economics and finance, education and teaching, physical and biomedical sciences, the environment, the law, government and politics, demography, psychology, sociology and sport all fall within the journal''s remit. The journal is therefore aimed at a wide statistical audience and at professional statisticians in particular. Its emphasis is on well-written and clearly reasoned quantitative approaches to problems in the real world rather than the exposition of technical detail. Thus, although the methodological basis of papers must be sound and adequately explained, methodology per se should not be the main focus of a Series A paper. Of particular interest are papers on topical or contentious statistical issues, papers which give reviews or exposés of current statistical concerns and papers which demonstrate how appropriate statistical thinking has contributed to our understanding of important substantive questions. Historical, professional and biographical contributions are also welcome, as are discussions of methods of data collection and of ethical issues, provided that all such papers have substantial statistical relevance.