当前位置: X-MOL 学术Perspect. Behav. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Priori Justification for Effect Measures in Single-Case Experimental Designs
Perspectives on Behavior Science ( IF 3.226 ) Pub Date : 2021-03-25 , DOI: 10.1007/s40614-021-00282-2
Rumen Manolov 1 , Mariola Moeyaert 2 , Joelle E Fingerhut 2
Affiliation  

Due to the complex nature of single-case experimental design data, numerous effect measures are available to quantify and evaluate the effectiveness of an intervention. An inappropriate choice of the effect measure can result in a misrepresentation of the intervention effectiveness and this can have far-reaching implications for theory, practice, and policymaking. As guidelines for reporting appropriate justification for selecting an effect measure are missing, the first aim is to identify the relevant dimensions for effect measure selection and justification prior to data gathering. The second aim is to use these dimensions to construct a user-friendly flowchart or decision tree guiding applied researchers in this process. The use of the flowchart is illustrated in the context of a preregistered protocol. This is the first study that attempts to propose reporting guidelines to justify the effect measure choice, before collecting the data, to avoid selective reporting of the largest quantifications of an effect. A proper justification, less prone to confirmation bias, and transparent and explicit reporting can enhance the credibility of the single-case design study findings.



中文翻译:

单一案例实验设计中效果测量的先验理由

由于单一案例实验设计数据的复杂性,许多效果测量可用于量化和评估干预的有效性。An inappropriate choice of the effect measure can result in a misrepresentation of the intervention effectiveness and this can have far-reaching implications for theory, practice, and policymaking. 由于缺少报告选择效果度量的适当理由的指南,第一个目标是在数据收集之前确定效果度量选择和理由的相关维度。第二个目的是利用这些维度构建用户友好的流程图或决策树,指导应用研究人员在此过程中。在预注册协议的上下文中说明了流程图的使用。这是第一项尝试提出报告指南以证明效果测量选择的合理性的研究,在收集数据之前,以避免选择性地报告最大量化的效果。适当的理由、不易出现确认偏差以及透明和明确的报告可以提高单案例设计研究结果的可信度。

更新日期:2021-03-25
down
wechat
bug