{"title":"Wishart 分布自由度的损失先验","authors":"Luca Rossini, Cristiano Villa, Sotiris Prevenas, Rachel McCrea","doi":"10.1016/j.ecosta.2024.04.001","DOIUrl":null,"url":null,"abstract":"Motivated by the proliferation of extensive macroeconomic and health datasets necessitating accurate forecasts, a novel approach is introduced to address Vector Autoregressive (VAR) models. This approach employs the global-local shrinkage-Wishart prior. Unlike conventional VAR models, where degrees of freedom are predetermined to be equivalent to the size of the variable plus one or equal to zero, the proposed method integrates a hyperprior for the degrees of freedom to account for the uncertainty in the parameter values. Specifically, a loss-based prior is derived to leverage information regarding the data-inherent degrees of freedom. The efficacy of the proposed prior is demonstrated in a multivariate setting both for forecasting macroeconomic data, and Dengue infection data.","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"2 1","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Loss-based prior for the degrees of freedom of the Wishart distribution\",\"authors\":\"Luca Rossini, Cristiano Villa, Sotiris Prevenas, Rachel McCrea\",\"doi\":\"10.1016/j.ecosta.2024.04.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Motivated by the proliferation of extensive macroeconomic and health datasets necessitating accurate forecasts, a novel approach is introduced to address Vector Autoregressive (VAR) models. This approach employs the global-local shrinkage-Wishart prior. Unlike conventional VAR models, where degrees of freedom are predetermined to be equivalent to the size of the variable plus one or equal to zero, the proposed method integrates a hyperprior for the degrees of freedom to account for the uncertainty in the parameter values. Specifically, a loss-based prior is derived to leverage information regarding the data-inherent degrees of freedom. The efficacy of the proposed prior is demonstrated in a multivariate setting both for forecasting macroeconomic data, and Dengue infection data.\",\"PeriodicalId\":54125,\"journal\":{\"name\":\"Econometrics and Statistics\",\"volume\":\"2 1\",\"pages\":\"\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2024-04-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Econometrics and Statistics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1016/j.ecosta.2024.04.001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ECONOMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Econometrics and Statistics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1016/j.ecosta.2024.04.001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0
摘要
广泛的宏观经济和健康数据集的激增需要准确的预测,在此背景下,我们引入了一种新方法来处理向量自回归模型(VAR)。这种方法采用了全局-局部收缩-威沙特先验。传统的 VAR 模型预先确定自由度等于变量大小加一或等于零,与此不同的是,所提出的方法为自由度整合了一个超先验,以考虑参数值的不确定性。具体来说,基于损失的先验值可以利用数据固有自由度的相关信息。在预测宏观经济数据和登革热感染数据的多变量设置中,演示了所提出的先验的有效性。
Loss-based prior for the degrees of freedom of the Wishart distribution
Motivated by the proliferation of extensive macroeconomic and health datasets necessitating accurate forecasts, a novel approach is introduced to address Vector Autoregressive (VAR) models. This approach employs the global-local shrinkage-Wishart prior. Unlike conventional VAR models, where degrees of freedom are predetermined to be equivalent to the size of the variable plus one or equal to zero, the proposed method integrates a hyperprior for the degrees of freedom to account for the uncertainty in the parameter values. Specifically, a loss-based prior is derived to leverage information regarding the data-inherent degrees of freedom. The efficacy of the proposed prior is demonstrated in a multivariate setting both for forecasting macroeconomic data, and Dengue infection data.
期刊介绍:
Econometrics and Statistics is the official journal of the networks Computational and Financial Econometrics and Computational and Methodological Statistics. It publishes research papers in all aspects of econometrics and statistics and comprises of the two sections Part A: Econometrics and Part B: Statistics.