Strasak Alexander M, Zaman Qamruz, Pfeiffer Karl P, Göbel Georg, Ulmer Hanno
Department of Medical Statistics, Informatics and Health Economics, Medical University Innsbruck, Schoepfstrasse 41, A-6020 Innsbruck, Austria.
Swiss Med Wkly. 2007 Jan 27;137(3-4):44-9. doi: 10.4414/smw.2007.11587.
Standards in the use of statistics in medical research are generally low. A growing body of literature points to persistent statistical errors, flaws and deficiencies in most medical journals.
In this paper we present a comprehensive review of common statistical pitfalls which can occur at different stages in the scientific research process, ranging from planning a study, through conducting statistical data analysis and documenting statistical methods applied, to the presentation of study data and interpretation of study results.
47 potential statistical errors and shortcomings, differentiated for the distinct phases of medical research are presented and discussed.
Statisticians should be involved early in study design, as mistakes at this point can have major repercussions, negatively affecting all subsequent stages of medical research. Consideration of issues discussed in this paper, when planning, conducting and preparing medical research manuscripts, should help further enhance statistical quality in medical journals.
医学研究中统计学使用的标准普遍较低。越来越多的文献指出，大多数医学期刊中存在持续的统计错误、缺陷和不足。
在本文中，我们对科学研究过程中不同阶段可能出现的常见统计陷阱进行了全面综述，从研究规划、进行统计数据分析和记录所应用的统计方法，到研究数据的呈现和研究结果的解释。
介绍并讨论了47种潜在的统计错误和不足，这些错误和不足因医学研究的不同阶段而有所区分。
统计学家应尽早参与研究设计，因为此时的错误可能产生重大影响，对医学研究的所有后续阶段产生负面影响。在规划、进行和准备医学研究手稿时考虑本文讨论的问题，应有助于进一步提高医学期刊的统计质量。
