Models, methods and inference for non-standard correlated data

复杂测量工具的出现产生了新的数据收集模式，导致非标准相关数据，通常涉及不同的反应，经常是离散和连续反应的混合，或纵向和生存结果，可能来自多个来源或不同的研究设计。由此产生的复杂结构通常需要非标准的统计方法，这些方法通常需要计算密集型的方法。这些在工程、金融、医学和健康领域的许多应用中特别常见。传统的工具通常依赖于假设数据，或者对数据进行一些适当的转换，遵循高斯分布，而这些工具并不直接适用于这些情况。******这里提出的研究涉及在非标准相关数据设置中应用的联合模型和方法的发展。它特别关注涉及由可能包含高维非标准相关响应的数据产生的复杂依赖结构的情况。特别强调的是开发和计算实施的新方法，供工程和医学/健康科学的从业人员使用。该研究有望为大数据时代的数据分析提供改进的、灵活的和强大的技术。

The advent of sophisticated tools of measurement has given rise to new modes of data collection resulting in non-standard correlated data, oftentimes involving disparate responses, frequently with a mixture of discrete and continuous responses, or of longitudinal and survival outcomes, and possibly from multiple sources or different study designs. The resulting complex structure typically requires non-standard statistical approaches that usually entail computationally intensive methodologies. These are particularly common in many applications in engineering, finance, and in medicine and health. Conventional tools that generally rely on the assumption that the data, or some suitable transformations of them, follow a Gaussian distribution, do not directly apply in these contexts.******The research proposed here concerns the development of joint models and methodologies for application in non-standard correlated data settings. It pays specific focus on situations involving complex dependence structures arising from data comprising possibly high-dimensional non-standard correlated responses. Particular emphasis is given on development and computational implementation of new methodologies for use by practitioners in engineering and the medical/health sciences. The proposed research is anticipated to yield improved, flexible, and powerful techniques for data analysis in the age of big data.