A review of statistical methods in the Korean Journal of Orthodontics and the American Journal of Orthodontics and Dentofacial Orthopedics

Lim, Hoi Jeong

Abstract

The purpose of this study was to investigate the changes and types of statistical methods used in the Korean Journal of Orthodontics (KJO) and the American Journal of Orthodontics and Dentofacial Orthopedics (AJODO) from 1999 to 2003. The frequency of use, transitions, assumption check of statistical methods and types of advanced statistical methods were examined from each journal. The study consisted of 247 articles published in the KJO and randomly chosen 50 articles per year which were original articles and used statistical methods. T-test, analysis of variance (ANOVA), correlation analysis, nonparametric analysis, regression analysis, chi-square test, factor analysis, were the order of statistical methods most frequently used in the KJO, while t-test, ANO VA, nonparametric analysis, correlation analysis, regression analysis, chi-square test, factor analysis, were the order of statistical methods used in the AJODO. The changes of statistical methods observed in the KJO were not significant (chi-square=17.4, p=0.6881), but the changes observed in the AJODO was seen to be significant (chi-square=42.4, p=0.0397). Some of the studies examined had overlooked the assumptions of the statistical methods employed. Data investigation such as outlier should be performed before analysis and alternative statistical approaches are applied for a small sample size. Types of advanced statistical methods were factor analysis and discriminant analysis in the KJO and Intention-To-Treat (ITT) analysis in clinical trials through multi-center, survival analysis and Generalized Estimating Equations (GEE) in the AJODO. Appropriate analysis approaches and interpretations should be applied for the correlated and repeated measurements of the orthodontic data set.