TYPE OF STATISTICAL TECHNIQUES IN RHEUMAT OLOGY AND INTERNAL-MEDICINEJOURNALS

A comparison of the prevalence and type of statistical analysis used i n internal medicine and rheumatology journals was done. Four represent ative journals of each specialty were selected and twelve original art icles were randomly obtained from each journal. The papers were review ed twice within a three month interval by the same evaluator following published definitions for classification. The rheumatology journals t ended to use fewer (80 versus 115) and simpler statistical techniques (X(3) = 4.28, DF = 1, p = 0.03; OR, 95% CI = 3.21, 1.05-10.85). There was a statistical difference in the utilization of statistical procedu res among journals in the four categories evaluated. Seven statistical techniques were required to have access to 86% of statistical tests u sed in rheumatology journals (t-tests, contingency tables, descriptive statistics, non-parametric comparisons, anova, multiple regression, a nd Pearson's correlation). The internal medicine journals required six statistical procedures to have access to 85% of the tests (contingenc y tables, survival analysis, epidemiologic statistics, t-tests, non-pa rametric statistics, and anova). Our results could be useful to plan m edical education in biostatistics emphasizing the statistical techniqu es most commonly used in these areas.