Hierarchical Statistical Modeling and Bayesian Melding for Occupational Exposure

职业暴露的分层统计模型和贝叶斯融合

• 批准号: 8733183
• 负责人: Sudipto Banerjee
• 金额: $ 0.74万
• 依托单位: UNIVERSITY OF MINNESOTA
• 依托单位国家: 美国
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-09-01 至 2014-09-14
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8733183
• 关键词: Hierarchical; Statistical; Modeling; Bayesian; Melding

DESCRIPTION (provided by applicant): We propose to develop innovative statistical tools for melding exposure models and field data arising from observations measured in a workplace. As a first step, we will construct a rich dataset of exposure scenarios in laboratory exposure chambers and real workplace settings, containing data on exposure determinants such as contaminant generation and ventilation rates and exposure measurements. We will develop a comprehensive and computationally feasible Bayesian statistical framework for melding the physical exposure models of occupational hygiene and experimental data from the workplace to effectively account for the sources of uncertainty and produce reliable statistical inference (estimation and predictions) for the system output (i.e., exposure) and inputs (i.e., exposure determinants). We will employ a Bayesian framework to validate physical models from monitoring data. Our framework will also include formal statistical measures for validating models with observed field data. We do so by assessing how adequately the models capture features and patterns in the monitoring data, applying sensitivity analysis to the choice of priors and choosing or selecting a model among a set of competing models. We will also develop and disseminate a user-friendly statistical software package that will enable occupational hygienists to implement the proposed methods for a wide variety of physical models to analyze their data in a seamless and convenient manner. Upon successful completion of the project, our developments will allow hygienists to systematically evaluate retrospective exposure, to predict current and future exposure in the absence of the working process or operation, and to estimate exposure with only a small number of air samples with possibly high variability. With only a few monitoring data points, our Bayesian melding framework will provide more precise estimates of exposure than monitoring. With advances in computational methods and inexpensive software implementation, we purport to exalt formal modeling to an indispensable position in the industrial hygienists' armory.

描述（由申请人提供）：我们建议开发创新的统计工具，用于融合暴露模型和在工作场所测量的观察结果所产生的现场数据。作为第一步，我们将在实验室暴露室和真实的工作场所环境中构建一个丰富的暴露场景数据集，其中包含有关暴露决定因素的数据，如污染物生成和通风率以及暴露测量。我们将开发一个全面的和计算上可行的贝叶斯统计框架，用于融合职业卫生的物理暴露模型和工作场所的实验数据，以有效地解释不确定性的来源，并为系统输出（即，曝光）和输入（即，暴露决定因素）。我们将采用贝叶斯框架来验证监测数据的物理模型。我们的框架还将包括正式的统计措施，用于验证模型与观测到的现场数据。我们这样做是通过评估如何充分的模型捕捉监测数据中的功能和模式，应用敏感性分析的先验选择和选择或选择一组竞争模型中的模型。我们亦会发展和发放一套方便使用的统计软件，让职业统计师能以无缝和方便的方式，把建议的方法应用于各种物理模型，分析他们的数据。在项目成功完成后，我们的发展将使专家能够系统地评估回顾性暴露，预测当前和未来的暴露在没有工作过程或操作，并估计暴露与只有少量的空气样本可能具有很高的可变性。只有几个监测数据点，我们的贝叶斯融合框架将提供更精确的估计暴露比监测。随着计算方法的进步和廉价的软件实现，我们声称要提升形式建模在工业企业家的军械库中不可或缺的位置。