Waddington Hugh, Aloe Ariel M, Becker Betsy Jane, Djimeu Eric W, Hombrados Jorge Garcia, Tugwell Peter, Wells George, Reeves Barney
International Initiative for Impact Evaluation, New Delhi, India.
University of Iowa, Iowa City, IA, USA.
J Clin Epidemiol. 2017 Sep;89:43-52. doi: 10.1016/j.jclinepi.2017.02.015. Epub 2017 Mar 27.
Rigorous and transparent bias assessment is a core component of high-quality systematic reviews. We assess modifications to existing risk of bias approaches to incorporate rigorous quasi-experimental approaches with selection on unobservables. These are nonrandomized studies using design-based approaches to control for unobservable sources of confounding such as difference studies, instrumental variables, interrupted time series, natural experiments, and regression-discontinuity designs.
We review existing risk of bias tools. Drawing on these tools, we present domains of bias and suggest directions for evaluation questions.
The review suggests that existing risk of bias tools provide, to different degrees, incomplete transparent criteria to assess the validity of these designs. The paper then presents an approach to evaluating the internal validity of quasi-experiments with selection on unobservables.
We conclude that tools for nonrandomized studies of interventions need to be further developed to incorporate evaluation questions for quasi-experiments with selection on unobservables.
严格且透明的偏倚评估是高质量系统评价的核心组成部分。我们评估对现有偏倚风险方法的修改，以纳入针对不可观测因素进行选择的严格准实验方法。这些是非随机研究，使用基于设计的方法来控制不可观测的混杂来源，如差异研究、工具变量、中断时间序列、自然实验和回归间断设计。
我们回顾现有的偏倚风险工具。借鉴这些工具，我们提出偏倚领域并为评估问题提供方向。
综述表明，现有的偏倚风险工具在不同程度上提供了不完整的透明标准来评估这些设计的有效性。本文随后提出了一种评估针对不可观测因素进行选择的准实验内部有效性的方法。
我们得出结论，干预措施的非随机研究工具需要进一步开发，以纳入针对不可观测因素进行选择的准实验的评估问题。
