摘要
临床研究中,统计学方法的准确应用关系到研究结果的可靠性和科学性。本文以典型案例解析方式,对临床研究中统计描述、统计推断、数据处理、结果解释的规范应用要点、常见误用进行总结分析,重点介绍了t检验与方差分析的误用、χ^(2)检验与配对χ^(2)检验的误用、回归分析中哑变量的设置、重复测量数据的分析方法与注意事项、随机缺失数据的填补方法、P值和关联性分析结果的谨慎解读,可为临床工作者在开展科研工作过程中规范应用统计学方法提供参考和依据,避免出现统计学方法的盲目套用和误用,从而提高临床科研的质量和水平。
The correct use of statistical methods are a ssociated with the reliability and scientificity of research results in clinical research.The key points and common misuses of statistical description,statistical inference,data processing and results interpretation in clinical research were summarized and analyzed through typical case analysis in this article.Misuse of t test and analysis of variance,misuse ofχ^(2) test and pairedχ^(2) test,dummy variable s etting of categorical independent variables in regression analysis,precautions for regression analysis of repeated measurement data,multiple imputation of missing data,prudent interpretation of P value and correlation analysis results were also stressed,to provide reference and basis for clinical workers to apply normative statistical methods in scientific research,and avoid the misuse of statistical methods,so as to improve the quality and level of clinical research.
作者
郑德强
段明瑞
李小春
侯锐
吴立娟
王友信
ZHENG Deqiang;DUAN Mingrui;LI Xiaochun;HOU Rui;WU Lijuan;WANG Youxin(Department of Epidemiology and Health Statistics,School of Public Health,Capital Medical University,Beijing Key Laboratory of Clinical Epidemiology,Beijing 100069,China)
出处
《中国卒中杂志》
2022年第1期43-50,共8页
Chinese Journal of Stroke
关键词
临床研究
假设检验
置信区间
回归分析
误用
Clinical research
Hypothesis testing
Confidence interval
Regression analysis
Misuse