Abstract
Aims: Statistical methods play an important role in medical and dental research. Therefore, the role of statisticians has become more important because of the increased use of more complex statistical methods. However, the authors seldom report who performed the statistical analysis. The aim of this study was to examine how often the contributor to statistical analysis was reported and if this was associated with the quality of statistical reporting and the use of advanced statistical methods in dental articles.
Methods: A total of 200 articles published in 2010 were analysed covering five dental journals: Journal of Dental Research, Caries Research, Community Dentistry and Oral Epidemiology, Journal of Dentistry and Acta Odontologica Scandinavica. Each paper underwent careful scrutiny for the use of statistical methods and reporting. A paper with at least one poor reporting item has been classified as “problems with reporting statistics”, and a paper without any poor reporting item as “acceptable”.
Results: A contributor to the data analysis was reported in 33 (16.5%) of the articles. When the data analyst was reported, 13 (39.4%) of the articles were classified as acceptable compared with 32 (19.2%) among those who had not reported who undertook the data analysis (p=0.014). Advanced statistical methods were used in 19 (57.6%) of the articles that reported who carried out the data analysis and in 44 (26.3%) of the articles where no information was given on the data analyst (p=0.001).
Conclusions: Reporting who carried out the data analysis was associated with higher proportion of acceptable papers. Thus the journals should include in the articles a section for contributors where it would be stated who performed the statistical analysis. This should improve the quality and reporting of statistical analysis as the named contributors take the responsibility of the analysis.
Get full access to this article
View all access options for this article.