|Title||Enhancing the interpretation of statistical P values in toxicology studies: implementation of linear mixed models (LMMs) and standardized effect sizes (SESs)|
|Author(s)||Schmidt, Kerstin; Schmidtke, Jörg; Kohl, Christian; Wilhelm, Ralf; Schiemann, Joachim; Voet, Hilko van der; Steinberg, Pablo|
|Source||Archives of Toxicology 90 (2016)3. - ISSN 0340-5761 - p. 731 - 751.|
|Publication type||Refereed Article in a scientific journal|
|Keyword(s)||90-day toxicity study - ANOVA - Linear mixed models - P values - Repeated measurements - Standardized effect sizes|
In this paper, we compare the traditional ANOVA approach to analysing data from 90-day toxicity studies with a more modern LMM approach, and we investigate the use of standardized effect sizes. The LMM approach is used to analyse weight or feed consumption data. When compared to the week-by-week ANOVA with multiple test results per week, this approach results in only one statement on differences in weight development between groups. Standardized effect sizes are calculated for the endpoints: weight, relative organ weights, haematology and clinical biochemistry. The endpoints are standardized, allowing different endpoints of the same study to be compared and providing an overall picture of group differences at a glance. Furthermore, in terms of standardized effect sizes, statistical significance and biological relevance are displayed simultaneously in a graph.