The consideration for methods of statistical analysis about the thesis published in the journal of korean oriental medical Ophthalmology & Otolaryngology & Dermatology from 2003 to 2005

2003년부터 2005년까지 안이비인후피부과 학회지에 게재된 논문들의 통계적 분석 방법에 대한 고찰

  • 김규석 (경희대학교 한의과대학 안이비인후피부과학교실) ;
  • 남혜정 (경희대학교 한의과대학 안이비인후피부과학교실) ;
  • 박외숙 (경희대학교 한의과대학 안이비인후피부과학교실) ;
  • 김희정 (경희대학교 한의과대학 안이비인후피부과학교실) ;
  • 차재훈 (경희대학교 한의과대학 안이비인후피부과학교실) ;
  • 김윤범 (경희대학교 한의과대학 안이비인후피부과학교실)
  • Published : 2006.12.25

Abstract

Objective : This study was carried out to investigate what type of assumption and conditions are needed for the application of various statistical techniques such as descriptive statistics, t-test, analysis of variance, correlation analysis, regression analysis and chi-square test and to evaluate that they are used correctly in the research process. Methods : One more methods of statistical analysis were used in 91 papers among 162 papers selected from the journal of Korean oriental medical Ophthalmology & Otolaryngology & Dermatology from April 2003 to December 2005. So we analysed the type of statistical analysis method in 91 papers(clinical and experimental study) and assessed the their validity of statistical techniques by the check list consisting of 34 items(3 items for validity assessment of descriptive statistics, 6 items for t-test, 7 items for analysis of variance, correlation analysis and regression analysis, respectively, 4 items for chi-square test) Results : 1. The type of 65(40%) cases is experimental trial, the type of 55(34%) cases is case report, the type of 26(16%) cases is clinical trial and the type of 16(10%) cases is review, in 91 papers using statistical techniques among 162 papers selected from the journal of Korean oriental medical Ophthalmology & Otolaryngology & Dermatol-ogy from April 2003 to December 2005. 2. One more methods of statistical analysis were used in the experimental and clinical study. When we classified 125 units using statistical analysis methods in 91 papers according to statistical techniques such as descriptive statistics, t-test, analysis of variance, correlation analysis, regression analysis and chi-square test, the number of independent sample t-test is 33(26%), the number of only descriptive statistics is 28(22%), the number of independent sample t-test is 33(26%), the number of only descriptive statistics is 28(22%), the number of one way ANOVA is 15(12%), the number of non-parametric test 10(8%). 3. After carrying out one way ANOVA, the number of using multiple comparison methods is 15(Scheffe:6(26%), Duncan:4(17%), Dunnett:3(13%), Tukey:2(9%)) out of 23 (total case carrying out one way ANOVA). 8(35%) out of 23 did not enforce multiple comparison methods after carrying out one way ANOVA. 4. From the assessment of validity about 63 cases using statistical techniques(except descriptive statistics), 5(8%) cases are proper, the other 58(92%) are improper, so we recognized a serious misuse of statistical application in our journal. 5. The number of case below 10 sample size in experimental and clinical study(except descriptive statistics) is 31(34%) and frequent. Also the number of case containing no mention of sample size is 41(45%, including culture study). 6. For example of statistical error, there are wrong choice of statistical technique, lack of check on standard assumption(such as standard distribution, equivariance, independence), and so on. Conclusions : We investigated the validity of statistical analysis methods in our journal by check list consisting of 34 items and suggested correct statistical analysis methods. We should practice the spread of education about statistical analysis methods and precis application, enhance objectivity and reliability of our thesis and further correspond with purpose of scientific study.

Keywords

statistical analysis method;descriptive statistics;t-test;analysis of variance;correlation analysis;multiple comparison