Premium
A method for evaluation of small sample, short duration experiments
Author(s) -
Betz Peter K.,
Ratcliff Perry A.,
Levin Joel R.,
Rothman Frederic L.
Publication year - 1968
Publication title -
journal of periodontal research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.31
H-Index - 83
eISSN - 1600-0765
pISSN - 0022-3484
DOI - 10.1111/j.1600-0765.1968.tb01938.x
Subject(s) - analysis of variance , cementum , nonparametric statistics , statistics , molar , bonferroni correction , statistical significance , statistical analysis , mathematics , normality , variance (accounting) , dentistry , orthodontics , medicine , accounting , dentin , business
The purpose of this study was to see if any statistically significant differences could be shown between groups when using small experimental samples in a short duration experiment. Because small samples were employed and because normality and equality of variance assumptions were doubtful, the «Kruskal‐Wallis» Nonparametric «One‐Way» Analysis of Variance by Ranks was performed on the data to test for statistical significance (Siegel 1956). The data suggest that, within the severe limits of this study, any of the alterations from normal caused changes in cementum. The effects of hypophysectomy, adrenocorticotropic hormone and somatotrophic hormone on the thickness of cementum of rat molar roots were investigated, using statistical methods which were able to show some between‐group differences when small samples were used in short experiments. Some of the anticipated changes in cementum with these hormones did not become apparent in the 32 rat molars during the 36 day experiment.