{"title":"Small area estimation under a spatially correlated multivariate area-level model","authors":"Saurav Guha, Hukum Chandra","doi":"10.1093/jrsssa/qnad079","DOIUrl":null,"url":null,"abstract":"\n Spatial version of multivariate Fay–Herriot model is introduced and small area predictor under this model is proposed. The residual maximum likelihood is employed for estimating the parameters of the proposed model. Analytical and bootstrap approaches for estimating the mean squared error (MSE) of the proposed predictor are also developed. The performance of the proposed predictor and the MSE estimators are evaluated through various simulation studies. The results evidently show that the proposed predictor outperforms the existing predictors. An application of the proposed methodology has also been made using the 2011–12 Consumer Expenditure Survey data of India.","PeriodicalId":49983,"journal":{"name":"Journal of the Royal Statistical Society Series A-Statistics in Society","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2023-06-19","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/qnad079","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
Abstract
Spatial version of multivariate Fay–Herriot model is introduced and small area predictor under this model is proposed. The residual maximum likelihood is employed for estimating the parameters of the proposed model. Analytical and bootstrap approaches for estimating the mean squared error (MSE) of the proposed predictor are also developed. The performance of the proposed predictor and the MSE estimators are evaluated through various simulation studies. The results evidently show that the proposed predictor outperforms the existing predictors. An application of the proposed methodology has also been made using the 2011–12 Consumer Expenditure Survey data of India.
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.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
