Low-dose risk bounds via simultaneous confidence bands

通过同时置信带确定低剂量风险界限

• 批准号: 7029589
• 负责人: WALTER W PIEGORSCH
• 金额: $ 0.63万
• 依托单位: UNIVERSITY OF SOUTH CAROLINA AT COLUMBIA
• 依托单位国家: 美国
• 财政年份: 1997
• 资助国家: 美国
• 起止时间: 1997-09-01 至 2006-08-15
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7029589
• 关键词: animal data; cancer risk; clinical research; data collection methodology /evaluation; dosage; environmental exposure; environmental toxicology; human data; mathematical model; model design /development; statistics /biometry

DESCRIPTION (provided by applicant): Quantifying environmental and other detrimental risks from exposure to hazardous agents is an important component in the process of risk evaluation and assessment. The primary goal of this project is to develop and study methods of simultaneous statistical inference for use in low-dose risk extrapolation. Application is directed to environmental and occupational risk assessment studies where human or animal data are used to set benchmark or other safe low-dose levels of a hazardous agent, but where study information is limited to high dose levels of the agent. Methods are emphasized for simultaneous upper confidence limits on predicted risk for proportion endpoints. From the simultaneous bounds, lower confidence limits on the benchmark dose (BMD) associated with a particular risk are calculated. An important feature of the simultaneous construction is that any inferences based on inverting the simultaneous confidence bounds apply automatically to inverse bounds on the BMD. The methodology extends previous results for simultaneous confidence bands to binomial and overdispersed proportion data under a series of link functions that describe the dose-response relationship. Consideration is also given to address model selection bias across the various link functions via computerized model adequacy appraisals. An evaluation phase of the project studies the small-sample operating characteristics of the methodology via Monte Carlo computer calculations. The new methods continue to fill existing gaps in low-dose risk extrapolation, and have application to the important problem of performing low-dose risk assessment with proportion data. World Wide Web software is constructed to allow the methods to be accessible to the widest possible corps of users.

说明（由申请者提供）：量化接触危险物剂的环境和其他有害风险是风险评价和评估过程中的一个重要组成部分。该项目的主要目标是开发和研究用于低剂量风险外推的同步统计推断方法。适用于环境和职业风险评估研究，其中使用人类或动物数据来确定基准或危险物剂的其他安全低剂量水平，但研究资料仅限于物剂的高剂量水平。方法强调的同时上限置信度的比例终点预测风险。从同步界限，与特定风险相关的基准剂量（BMD）的置信下限计算。同时建设的一个重要特点是，任何推理的基础上反演的同时置信界限自动适用于反BMD的界限。 该方法扩展了以前的结果，同时置信带二项式和过度分散的比例数据下的一系列链接功能，描述了剂量-反应关系。还考虑通过计算机化模型充分性评估来解决各种链接功能的模型选择偏差。该项目的一个评价阶段通过蒙特卡罗计算机计算研究该方法的小样本操作特性。这些新方法继续填补低剂量风险外推方面的现有空白，并适用于利用比例数据进行低剂量风险评估这一重要问题。万维网软件的设计是为了使尽可能多的用户能够使用这些方法。