Bayesian Methods for Epidemiologic Studies

拟议的研究方案旨在开发贝叶斯统计方法，用于估计和推断在流行病学研究研究分析中常见的统计模型。 拟议的方法将在三大主题下描述：1)在没有金标准的情况下评估诊断测试的方法， 2)评价诊断试验所需样本量的确定方法；3)随机对照试验的荟萃分析方法。 贝叶斯框架的优点包括，它们提供的结果易于解释，它们可以很容易地用于估计非常复杂的模型，并且它们允许在需要时使用收集的数据之外的信息。 传统上，推广贝叶斯方法的一个重要障碍是缺乏软件。因此，将开发用户友好的软件，以配合每一种拟议的方法。 每个主题将产生几个适合研究生或博士后研究员的子项目。

The proposed research program is directed towards development of Bayesian statistical methods for estimation and inference of statistical models that commonly arise in the analysis of epidemiological research studies. The proposed methods will be described under three broad themes: 1) Methods for the evaluation of a diagnostic test in the absence of a gold-standard, 2) Methods for determining the sample size required for evaluating diagnostic tests, 3) Methods for meta-analysis of randomized controlled trials. Advantages of the Bayesian framework include that they provide results that are easy to interpret, that they can be easily applied to estimate very complex models and that they allow for the possibility of using information external to the data collected when required. Traditionally, an important impediment in disseminating Bayesian methods has been the lack of software. Therefore, user-friendly software will be developed to accompany each of the proposed methods. Each theme will give rise to several sub-projects suitable for graduate students or post-doctoral fellows.