Statistics for the analysis of tenderness score summation in patient with craniomandibular disorders

Abstract

Digital palpation has been used to evaluate patients with craniomandibular disorders. Tenderness at each site is classified on a 0 to 3 scale and evaluated as total summation. Tendernes were ranked on the scale.Nonparametric statistics were applied to analyze these data. 34 kind 64 sites makes 192 steps in total summation. Increase of step yielded similer results in parametric and nonparametric statistics. The purpose of this study is to clarify the difference in results between non parametric and parametric statistics. 100 female CMD patient data were used to make group of 13,25,50 and 100 subject group. 16 kind 30 sites, 23 kind 44 sites and 34 kind 64 sites were anlysed as summation. The Wilcoxon test and t-test were used to analyse before and after treatment data. The Spearman's correlation coefficient and Pearson's correlation coefficient were analyzed. In the probability, nonparametric statistics always showed more conservative result than parametric statistics.Discrepancy between nonparametric and parametric statistics decreased with an increase of the number of subjects. With 50 subjects, the maximum discrepancy was 0.0011. Discrepancy between correlation also decreased with an increase of the number of subjects. With 50 subjects, the maximum discrepancy was 0.0095. There found very little difference if the number of subjects is more than 50.