Inference for copula-based dependence models with discrete or incomplete data

具有离散或不完整数据的基于 copula 的依赖模型的推理

• 批准号: 386698-2010
• 负责人: Neslehova, Johanna
• 金额: $ 1.46万
• 依托单位: McGill University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2013
• 资助国家: 加拿大
• 起止时间: 2013-01-01 至 2014-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=529021
• 关键词: Inference; copula; based; dependence; models

This research proposal is concerned with dependence between random variables. This phenomenon is of prime concern in many fields, including health sciences, biostatistics and hydrology, not to speak of finance and insurance. An example is provided by dependent survival times, which are often encountered in clinical and epidemiological research, e.g., in family studies, progression data or recurrent events. Copulas are becoming increasingly popular as a tool for the characterization and study of stochastic dependence, mainly due to their great flexibility in modeling the variables' individual behavior. Statistical inference for these models is only beginning to emerge and the proposed research aims at contributing towards its development.

本研究提案涉及随机变量之间的依赖性。这种现象在健康科学、生物统计学和水文学等许多领域备受关注，更不用说金融和保险了。依赖生存时间就是一个例子，这在临床和流行病学研究中经常遇到，例如在家庭研究、进展数据或复发事件中。 Copula 作为表征和研究随机依赖性的工具变得越来越流行，这主要是因为它们在对变量的个体行为进行建模时具有很大的灵活性。这些模型的统计推断才刚刚开始出现，拟议的研究旨在为其发展做出贡献。