The reporting of statistical inferences in selected prosthodontic journals

Dental periodicals are the fundamental source of prosthodontic research. The ability to understand and contribute to dental literature is basic to the prosthodontic profession. The purpose of this study is to tally relative frequency with which various descriptive (n = 18), graphical (n = 7), and inferential statistical procedures (n = 68) are used in the prosthodontic literature. Our method consists of four procedures: journal selection, choice of 1987 through 1988 articles with inferential statistical content, tally of the statistical procedures in those articles, and quality control procedures used in obtaining these data. At least 50% of 10 prosthodontists selected 17 of 100 journals most likely to be read by prosthodontists. In the 17 journals, 1,320 articles were screened of which 406 were selected and evaluated for their statistical procedures. The bar and line plots were the most common graphical procedures occurring in over one fourth of the 406 articles. Percentages, means, and standard deviations occurred in more than 40%. Although 58% used the .05 significance level, only 0.3% mentioned power. Analysis of variance was used more often than the t tests (42% v 29%), whereas correlation/regression (21%) and chi-square tests (14%) were used less often. The t tests, analysis of variance (Duncan, Tukey, and Student-Newman-Keuls multiple comparison procedures), chi-square tests, correlation and regression, and the Wilcoxon tests occurred in at least 5% of the 406 articles.