Spatiotemporal Modelling

时空建模

• 批准号: 1000232011-2017
• 负责人: Simpson, Daniel
• 金额: $ 8.74万
• 依托单位: University of Toronto
• 依托单位国家: 加拿大
• 项目类别: Canada Research Chairs
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=665253
• 关键词: Spatiotemporal; Modelling

Carefully modelling spatiotemporal data vital in fields as diverse as ecology, epidemiology, and fisheries science. As the size of datasets increases, so does the complexity of the associated statistical models. Dr. Simpson will develop improved Bayesian modelling pipelines to deal with the spatiotemporal models of real-world data. The effort spans issues of model specification, posterior computation, model checking, visualisation, and interpretation of results. The advances will be implemented in the popular R-INLA and Stan software packages, and are expected to have an impact in a number of areas of applied scientific research.

仔细模拟时空数据至关重要的领域，如生态学，流行病学和渔业科学。随着数据集规模的增加，相关统计模型的复杂性也在增加。辛普森博士将开发改进的贝叶斯建模管道来处理现实世界数据的时空模型。努力跨越了模型规范、后验计算、模型检查、可视化和结果解释等问题。这些进展将在流行的R-INLA和Stan软件包中实施，预计将对应用科学研究的许多领域产生影响。