Holford T R, Stack C
Department of Epidemiology and Public Health, Yale University School of Medicine, New Haven, Connecticut, USA.
Stat Methods Med Res. 1995 Dec;4(4):339-58. doi: 10.1177/096228029500400405.
Exposure measurement error in epidemiological studies is recognized as a feature that must be considered because of the potential bias that can result in estimates of the exposure-disease association. Most of the work to date has focused on methods of analysis that adjust for the resultant bias, but the implications of this work to the design of epidemiologic studies is not as well understood. An overview of the issues involved in the use of methods for dealing with errors in exposure information is discussed along with some design options that have been proposed for providing information necessary for their use. Validation studies compare somewhat crude and inexpensive measures of exposure to a gold standard, and study designs that incorporate these into the overall plan can realize some advantages in terms of cost. In addition, repeated assessments of exposure can realize efficiency for measures of exposure that are unbiased. However, much work remains to be done in the development of efficient designs for studying disease aetiology and prevention.
在流行病学研究中,暴露测量误差被视为一个必须考虑的因素,因为它可能导致暴露与疾病关联估计值出现潜在偏差。迄今为止,大部分工作都集中在分析方法上,以调整由此产生的偏差,但这项工作对流行病学研究设计的影响尚未得到充分理解。本文讨论了使用暴露信息误差处理方法所涉及的问题,并介绍了一些为使用这些方法提供必要信息而提出的设计选项。验证研究将相对粗略和廉价的暴露测量方法与金标准进行比较,将这些方法纳入总体计划的研究设计在成本方面可以实现一些优势。此外,对暴露进行重复评估可以提高无偏暴露测量的效率。然而,在开发用于研究疾病病因和预防的高效设计方面,仍有许多工作要做。