正确利用参加者结果对药品检测领域能力验证项目进行合理评价

    Optimizing Participant-derived Statistics for Robust Proficiency Assessment in Pharmaceutical Testing

    • 摘要:
      目的 帮助能力验证提供者正确利用参加者结果确定能力评定统计量及其中的指定值和能力评定标准差,从而确保能力评定结论的有效性。
      方法 为降低“利用参加者结果确定统计量”这一方法本身的局限性可能对能力评定结果产生的不利影响,本研究对国际标准化组织发布的准则、中国合格评定国家认可委员会出台的认可准则及指南性文件、相关部门颁布的中华人民共和国国家标准以及计量技术规范中的技术要求进行系统梳理:对其中涉及的统计学相关知识进行拓展介绍和深入解读;着重从数据审查、可供选择的常用统计方法及其应用条件、各统计算法的性能指标等关键环节展开全面分析。
      结果 汇总出利用参加者结果确定能力评定统计量这种方法的优缺点。
      结论 本研究通过具体示例诠释了“没有任何统计方法可以完美适合所有情境”的基本理念,并据此提示能力验证提供者应在运作计划过程中高度重视统计学方法的正确选择和使用。

       

      Abstract:
      OBJECTIVE To offer methods for proficiency testing providers to correctly apply the performance statistics that includes assigned value and standard deviations from participant results, thereby ensuring the validity of proficiency evaluation conclusions.
      METHODS To mitigate the potential adverse effects of the inherent limitations of the "use of participant results to determine statistical measures" method on competency assessment outcomes, this study systematically reviewed the technical requirements outlined in the guidelines issued by the International Organization for Standardization, the accreditation criteria and guidance documents released by the China National Accreditation Service for Conformity Assessment, the national standards of the People's Republic of China promulgated by relevant departments, and the metrological technical specifications. It provided an expanded introduction and in-depth interpretation of the statistical knowledge involved. A comprehensive analysis was conducted, focusing on key aspects such as data review, commonly available statistical methods and their application conditions, and the performance metrics of various statistical algorithms.
      RESULTS The advantages and disadvantages of the determination of criteria for evaluation of performance from data obtained in the same round of a proficiency testing scheme were summarized.
      CONCLUSION This study illustrates the fundamental principle that "no statistical method is universally perfect for all scenarios" through concrete examples, thereby reminding proficiency testing providers to place high importance on the proper selection and application of statistical methods during operational planning.

       

    /

    返回文章
    返回