Institute of Dentistry and University Hospital, University of Oulu, Oulu, Finland.
Acta Odontol Scand. 2009;67(4):206-11. doi: 10.1080/00016350902837922.
To investigate development of the use of statistical methods in dental journals in 1996, 2001, and 2006 hypothesizing that methods are becoming more sophisticated.
All original research articles in four dental journals in 1996, 2001, and 2006 were reviewed: Journal of Dental Research (JDR), Caries Research (CR), Community Dentistry and Oral Epidemiology (CDOE) and Acta Odontologica Scandinavica (AOS). Evaluation covered 928 articles reporting original research findings based on systematic collection and statistical analysis of research data. Aspects measured were: research design, statistical methodology, description of procedures, and presentation of results. Percentage frequencies of reported statistical procedures were compared between journals and between years.
The main findings of the study are: 1) that use of multivariate or specific methods did not increase from 1996 to 2006, 2) that traditional statistical significance testing is still widely used in dental journals and that use of confidence intervals increased in the period 1996 to 2006, 3) that statistical procedures are usually extensively described, and 4) that dental journals have different profiles in their statistical content.
The authors of articles in dental journals might apply these results when designing their dental research, i.e. to use statistical methods and to present results in line with the policy and presentation of the leading dental journals.
研究 1996 年、2001 年和 2006 年口腔医学期刊中统计方法的使用情况，假设方法变得更加复杂。
回顾了 1996 年、2001 年和 2006 年四份口腔医学期刊中的所有原始研究文章：《牙研究杂志》（JDR）、《龋病研究》（CR）、《社区牙科与口腔流行病学》（CDOE）和《斯堪的纳维亚口腔学报》（AOS）。评估涵盖了基于系统收集和统计分析研究数据的 928 篇报告原始研究结果的文章。测量的方面包括：研究设计、统计方法、程序描述和结果呈现。比较了各期刊和各年份报告统计程序的频率百分比。
研究的主要发现是：1）1996 年至 2006 年，多变量或特定方法的使用并未增加；2）传统的统计显著性检验仍广泛应用于口腔医学期刊，1996 年至 2006 年期间置信区间的使用增加；3）统计程序通常得到广泛描述；4）口腔医学期刊在统计内容方面存在不同的特点。
口腔医学期刊文章的作者在设计其口腔研究时可以应用这些结果，即使用统计方法并根据主要口腔期刊的政策和呈现方式呈现结果。
