The Russian National Research Medical University named after N.I. Pirogov; Endocrinology Research Center; Russian Society for Evidence Based Medicine.
Russian Society for Evidence Based Medicine.
Probl Endokrinol (Mosk). 2021 Oct 19;67(6):11-17. doi: 10.14341/probl12797.
In evidence-based medicine, the research methodology is determined by the risks of systematic biases and incorrect data analysis. Minimizing both risks increases the internal validity of the study. There are numerous recommendations and guidelines for data analysis and reporting, but the international community has not yet developed a questionnaire for reviewers to assess the quality of statistical analysis.
To develop a tool for formalized assessment of the quality of statistical analysis presented in scientific medical publications.
The questionnaire was developed based on the authors' decades of experience in statistical data analysis and reviewing the statistical aspects of biomedical articles and dissertations. The SAMPL guidelines, ICH E9, and other guidelines were taken into account when developing the questionnaire. Internal validation of the questionnaire was based on an independent assessment by two experts of 20 randomly selected articles on randomized controlled trials (RCTs) from elibrary.ru, and further statistical analysis of the agreement of experts' conclusions.
The CORSTAN (CORrect STatistical ANalysis) questionnaire was developed, which consists of two parts: the first part (10 questions) is intended for evaluating studies of any designs, while the second (following eight questions) is for additional assessment of RCTs. A stratification of the risk of incorrect statistical analysis is proposed. The evaluation of the questionnaire's internal validity showed its substantial and almost perfect agreement for each question and each article both in the sum of points and risk level.
The use of the questionnaire will simplify and harmonize the statistical review of publications and manuscripts in various institutions - scientific journals, dissertation boards, etc. The questionnaire can also be helpful for authors during preparing manuscripts; it will also help improve the quality of publications and research itself. We plan to improve the questionnaire as we gain experience in its application.
在循证医学中，研究方法学取决于系统性偏倚和数据分析错误的风险。最小化这两种风险可提高研究的内部有效性。有许多数据分析和报告的建议和指南，但国际社会尚未开发出用于评估统计分析质量的评审员问卷。
开发一种工具，用于正式评估科学医学出版物中呈现的统计分析质量。
该问卷是基于作者在统计数据分析和评审生物医学文章和论文的统计方面的数十年经验而开发的。在开发问卷时，考虑了 SAMPL 指南、ICH E9 和其他指南。问卷的内部验证基于两位专家对从 elibrary.ru 随机选择的 20 篇随机对照试验（RCT）文章的独立评估，以及对专家结论一致性的进一步统计分析。
开发了 CORSTAN（正确的统计分析）问卷，它由两部分组成：第一部分（10 个问题）用于评估任何设计的研究，第二部分（以下 8 个问题）用于对 RCT 进行额外评估。提出了不正确统计分析风险的分层。问卷内部有效性的评估表明，对于每个问题和每个文章，其在总分和风险水平上都具有实质性和近乎完美的一致性。
使用问卷将简化和协调各个机构（科学期刊、论文委员会等）的出版物和手稿的统计审查。问卷也可以帮助作者在准备手稿时；它还有助于提高出版物和研究本身的质量。我们计划在应用问卷的过程中不断改进它。
