Welch and Gabbe reviewed all articles published in the Americal Journal of Obstetrics and Gynecology during the first half of 1994 to assess the quality of the statistical application.
Of the 190 published articles 53 (28%) did not include a statistical analysis, 8 of which requiring an analysis. The number of reviewed articles were therefore 145. In about half of these (53%) the description of the analysis was inappropriate or incomplete and the possibility to assess the appropriateness severely limited. The number of articles with appropriate usage of statistics was 44 (30%) and the number of articles with inappropriate usage was 46 (32%). Of the 46 articles with inappropriate usage 27 (59%) had serious flaws.
The authors conclude that the lack of complete and detailed description of the applied statistics made it difficult to assess the appropriateness, and that more detailed guidelines for the description of statistics was needed. They add that a policy of statistical review should be instituted.
Welch GE, Gabbe SG. Review of statistics usage in the American Journal of Obstetrics and Gynecology. Am J Obstet Gynecol 1996;175:1138-1141.