Statistical techniques reported in pathology journals during 1983-1985. Implications for pathology educators.

The increasingly scientific basis of medicine challenges pathology educators to incorporate quantitative skills into a very compressed curriculum. One strategy is to focus training on the statistical techniques pathologists will most commonly encounter in their literature. We identified the reporting of statistical techniques in nearly 5200 original articles published during 1983-1985 in 16 journals important to pathology. Our results suggest that a reader familiar with 12 fundamental statistical concepts can evaluate knowledgeably over 95% of the quantitative findings reported in these journals. With the exception of survival analysis and pharmacologic modeling, these techniques are typically encountered in many introductory statistical texts. In numerous articles, failure to identify the statistical methodology used made it impossible to identify the analytic procedures used and, hence, judge the scientific validity of results.

Spectrum and frequency of use of statistical techniques in psychiatric journals.

Educators in psychiatry face an important challenge in deciding what quantitative skills to teach and where in the educational agenda to teach them. One strategy is to focus the quantitative training of psychiatrists on techniques they need to be effective consumers of their literature. The authors catalogued the statistical methods described in 15 major psychiatric journals during 1983 and 1984. A dozen procedures, typically encountered in intermediate-level statistics courses, accounted for approximately 95% of all the statistical methods reported. Readers of psychiatric journals also routinely encounter multivariate, nonparametric, and categorization techniques. Educators might apply these results in designing exposure to statistical skills for future psychiatrists.