ReviewExperimental toxicology: Issues of statistics, experimental design, and replication

•Replication failure is frequently the result of underpowered experiments.•Statistical significance is not, by itself, a sufficient determinant of an experimental outcome.•Randomized, replicated, and blind experimentation leads to improved experimental replication.•Researchers should avoid overstating experimental outcomes.

The difficulty of replicating experiments has drawn considerable attention. Issues with replication occur for a variety of reasons ranging from experimental design to laboratory errors to inappropriate statistical analysis. Here we review a variety of guidelines for statistical analysis, design, and execution of experiments in toxicology. In general, replication can be improved by using hypothesis driven experiments with adequate sample sizes, randomization, and blind data collection techniques.