Statistics usage in the American Journal of Obstetrics and Gynecology: Has anything changed?

OBJECTIVE: Our purpose was to compare statistical listing and usage between articles published in the American Journal of Obstetrics and Gynecology in 1994 with those published in 1999. STUDY DESIGN: All papers included in the obstetrics, fetus-placenta-newborn, and gynecology sections and the transactions of societies sections of the January through June 1999 issues of the American Journal of Obstetrics and Gynecology (volume 180, numbers 1 to 6) were reviewed for statistical usage. Each paper was given a rating for the cataloging of applied statistics and a rating for the appropriateness of statistical usage, when possible. These results were compared with the data collected on a similar review of articles published in 1994. RESULTS: Of the 238 available articles, 195 contained statistics and were reviewed. In comparison to the articles published in 1994, there were significantly more articles that completely cataloged applied statistics (74.3% vs 47.4%) (P< .0001), and there was a significant improvement in appropriateness of statistical usage (56.4% vs 30.3%) (P< .0001). CONCLUSION: Changes in the Instructions to Authors regarding the description of applied statistics and probable changes in the behavior of researchers and Editors have led to an improvement in the quality of statistics in papers published in the American Journal of Obstetrics and Gynecology. (Am J Obstet Gynecol 2002;186:584-6.)