|
Abstract:
|
In an aquatic toxicity test, responses of interest are observed from testing organisms exposed to various concentration levels of the testing chemical and the adverse effect of the chemical on the responses are then evaluated and quantified as a function of the concentration levels via statistical analysis. Such aquatic toxicity test often utilizes experimental outcomes from a single experiment while it is common that the particular laboratory have a history of conducting such experiments using the same testing organism species, chemical and experimental protocols. The sample size determination (SSD) is a crucial aspect of the experimental design in such tests. Adopting the Bayesian perspective, we use a simulation-based Bayesian approach to determine the sample size needed in such tests with prior using the historical experimental outcomes.The proposed approach is illustrated for the experiments with three different biological endpoints of interest: survival (dichotomous response), fecundity (counts), and biomass/growth (continuous response).
|
