Recommendations to improve use and reporting of statistics in animal experiments
Author:
- 1 December 2022
- journal article
- review article
- Published by SAGE Publications in Laboratory Animals
- Vol. 57 (3) , 224-235
Abstract
Flaws in experimental statistics are a major contributor to the poor reproducibility of animal experiments. Informed decisions about whether conclusions are justified requires clear reporting of experimental data and the statistical methods used to analyse them. When data are misinterpreted, manipulated or concealed to generate publications, it creates an illusion that chance observations are robust data which confirm the hypotheses presented. Attempts to reproduce and advance such observations can propagate large areas of irreproducible science. This hinders scientific progress, erodes public support for research, damages reputations and wastes resources. This review analyses and explains recommendations to improve use and reporting of statistics in animal experiments.Keywords
This publication has 91 references indexed in Scilit:
- Progress in Using Systematic Reviews of Animal Studies to Improve Translational ResearchPLOS Medicine, 2013
- Six red flags for suspect workNature, 2013
- Improving basic and translational science by accounting for litter-to-litter variation in animal modelsBMC Neuroscience, 2013
- Raise standards for preclinical cancer researchNature, 2012
- Replicates and repeats—what is the difference and is it significant?EMBO Reports, 2012
- Beyond Repeated-Measures Analysis of VarianceRegional Anesthesia & Pain Medicine, 2012
- Retracted Science and the Retraction IndexInfection and Immunity, 2011
- Show the data, don't conceal themBritish Journal of Pharmacology, 2011
- Error bars in experimental biologyJournal of Cell Biology, 2007
- Why Most Published Research Findings Are FalsePLOS Medicine, 2005