In recent years, there has been a decline in the quality of statistical reporting in biomedical scientific journals. The aim of this survey study was to find out the opinions of the World Association of Medical Editors (WAME) members on statistical reviews conducted in their journals, and to summarize the related recommendations that should be implemented in this area. A survey containing 25 questions on a range of aspects related to statistical peer review was distributed to WAME members and editorial staff of the journals they are affiliated with. The survey was completed by 141 individuals, the largest proportion of whom were editors‑in‑chief (36.9%). According to 40% of the respondents, only 31%-50% of the manuscripts accepted for publication are statistically correct. The higher the respondents' assessment of their own statistical knowledge, the lower they believed this percentage to be (P = 0.02). The frequency of statistical peer review was estimated by most respondents at only 1%-10% of the submitted manuscripts. The main reasons for this included difficulty in finding reviewers with the right skills and a lack of funding in this area. Among the respondents working for journals without a statistical editor on the editorial board, 49% believed that statistical reviews enhance the quality of published manuscripts, whereas among those confirming a presence of a statistical editor, this percentage was as high as 84% (P <0.001). Only 5% of the respondents stated that their journal uses the Statistical Analyses and Methods in the Published Literature recommendations. Nowadays, members of editorial boards face significant problems related conducting statistical reviews for their journals. For this reason, it is imperative to start implementing statistical guidelines for biomedical journals.
Read full abstract