观察性药物流行病学研究的P值相关问题探讨  

Common problems related to P-value in observational pharmacoepidemiological studies

作　　者：黎国威 李立康 刘颖欣 王若婷 吴大嵘 LI Guowei;LI Likang;LIU Yingxin;WANG Ruoting;WU Darong(Guangdong Second Provincial General Hospital,Guangzhou Guangdong 510317,China;Guangdong Provincial Hospital of Chinese Medicine,Guangdong Provincial Academy of Chinese Medical Sciences,The Second Affiliated Hospital of Guangzhou University of Chinese Medicine,Guangzhou Guangdong 510120,China)

机构地区：[1]广东省第二人民医院,广东广州510317 [2]广东省中医院,广东省中医药科学院,广州中医药大学第二附属医院,广东广州510120

出　　处：《中国药物警戒》2022年第1期23-26,共4页Chinese Journal of Pharmacovigilance

基　　金：国家重点研发计划(2019YFC1709800、2019YFC1709802)。

摘　　要：目的探索观察性药物流行病学研究中P值相关的常见问题。方法通过文献研究结合专家经验等途径进行叙述性综述。结果在观察性药物流行病学研究中,P值的常见问题包括容易被错误解读与被人为操纵、基于P值是否小于0.05进行一刀切来判断结论是否具有统计学意义等,这些常见问题极容易损害药物流行病学研究结论的可重复性与真实有效性。结论药物流行病学研究容易出现P值的相关问题。通过综合提高对P值等基本概念的教育水平等多渠道,规范科学研究和临床实践,结合多方的联动努力,才能减缓当前P值不当使用的窘况,提高观察性药物流行病学研究结论的真实有效性与可重复性。Objective To explore the common problems related to P-value in observational pharmacoe-pidemiological studies.Methods A combination of literature research and expert opinions was used for this review.Results The common problems related to P-value in observational pharmacoepidemiological studies included myths,misuse,manipulation and dichotomization of P-value.These problems could compromise the validity and reproducibility of findings and conclusions in pharmacoepidemiological studies.Conclusion Problems related to P-value often occur in observational pharmacoepidemiological studies.An integrated approach that involves advancing researchers’understanding of P-value,enhancing the quality and integrity of research and clinical practices,and ensuring proper use of P-value in the research community will help minimize the misuse of P-value in pharmacoepidemiological studies.

关 键 词：药物流行病学 P值 统计学 观察性研究 

分 类 号：R994.11[医药卫生—毒理学]