摘要
目的 总结并统计中、美放射学核心期刊Radiology、American Journal of Roentgenology （A JR）、中华放射学杂志（Chinese Journal of Radiology,CJR）和放射学实践（Radiologic Practice,RP）中使用的统计学方法的类型、频率差异.方法 搜集2012年9月到2013年8月发表在Radiology、A JR、JR和RP期刊上的文章,文章纳入标准：选择原创性科技论文,包含研究目的、方法、结果与结论;同时排除病例数＜10的论文、综述文献、病例读片、图文讲座、病例报告（病例数＜10例）、学术争鸣、社论、信件、会议纪要、新闻等.首先根据统计学分类方法将所有文章中涉及的统计学方法分为18大类,并明确各类型统计学方法的范围;其次确定每篇文章中所使用的统计学方法,并按18种统计方法的原理进行相关归类统计;最后对中、美期刊所使用的各种统计方法的频率进行x2检验.结果 共1077篇文章符合纳入标准,累计使用统计学方法1911次.中、美期刊分别为488、589篇,其中CJR 210篇（19.498％）、RP278篇（25.813％）、AJR247篇（22.934％）、Radiology 342篇（31.755％）;227篇（21.077％）文章未使用统计学方法,CJR 54篇（5.014％）、RP127篇（11.792％）、A JR 31篇（2.878％）、Radiology15篇（1.393％）篇;Radiology统计学方法使用频率最高.中、美期刊文章总的统计学方法频数分别为520（27.211％）、1391次（72.789％）,差异具有统计学意义（x2=197.836,P＜0.01）;中、美期刊论文基本统计学方法的使用频次分别为220（11.512％）、429次（22.449％）,相关与回归分析的使用频数分别为52（2.721％）、245次（12.820％）,方差分析使用频数分别为31（1.622％）、98次（5.128％）,非参数检验使用频数分别为67（3.506％）、216次（11.302％）,美国期刊均高于中国期刊,差异具有统计学意义（x2值分别为138.197、137.549、135.794、138.197,P值均＜0.01）.结论 中、美影像期刊论文使用统计学方法差异较大,原因较多,科研人员应遵从科学的设计并合理选择统计学方法,提高科研论文质量.
Objective To determine the types of statistical methods and their frequency used in major articles published in American and Chinese prestigious radiology journals,including Radiology,American Journal of Roentgenology （A JR）,Chinese Journal of Radiology （C JR） and Radiologic Practice （RP）.Methods One thousand and seventy-seven major articles published in Radiology,A JR,C JR and RP between September 2012 and August 2013 were retrospectively analyzed.The articles were exclusively original reports with objective,material and method,results and conclusion.All other articles,including case reports （fewer than 10 patients）,review articles,pictorial essays,editorials,letters,and news items,were excluded from the study.The statistical method appearing in each article was assigned to one of eighteen categories （e.g.,basic t-test,x2 test,correlation and regression techniques,ANOVA,nonparametric statistics）,and difference of the frequency between the American and the Chinese prestigious journals was assessed using Chi-square test.P＜0.05 denoted statistical significance.Results One thousand and seventy-seven major articles included C JR （n=210,19.498％）,RP （n=278,25.813％）,A JR （n=247,22.934％）,and Radiology （n=342,31.755％）.Two hundred and twenty-seven articles （21.077％） used no statisticalmethods or only descriptive statistics,including C JR （n=54,5.014％）,RP （n=127,11.792％）,A JR （n=31,2.878％）,and Radiology （n=15,1.393％）.Statistical methods were most frequently used in Radiology.There was statistical difference of frequency between the American （n=1391,72.789％） and the Chinese prestigious radiology journals （n=520,27.211％） （x2=197.836,P＜0.01）.Basic statistical methods were more likely to be found in the articles of American journals （n=429,22.449％） than that in the Chinese journals （n=220,11.512％） （x2=138.197,P＜0.01）.Correlation,regression analysis,ANOVA,and nonparametric statistics were more often used in the articles of American journals than that in the Chinese journals,which were n=245,12.820％ versus n=52,2.721％ （x2=137.549,P＜0.01） for correlation and regression analysis,n=98,5.128％versus n=31,1.622％ （x2=135.794,P＜0.01） for ANOVA,and n=216,11.302％ versus n=67,3.506％ （x2=138.197,P＜0.01） for nonparametric statistics.Conclusions The types of statistical methods and their frequency are quite different between the Chinese and the American prestigious radiology journals.Scientific research people should follow the scientific design and use ureasonable statistical methods to improve the quality of research papers.
出处
《中华放射学杂志》
CAS
CSCD
北大核心
2014年第9期772-776,共5页
Chinese Journal of Radiology
