Understanding toxic effects on biological populations across generations is crucial for determining t
he long-term consequences of c
hemical pollution in aquatic environments. As a consequence, t
here is considerable demand for suitable statistical met
hods to analyze complex multigeneration experimental data. We demonstrate t
he application of a Bayesian mixture model (wit
h random-effects) to assess t
he effect of intergeneration copper (Cu) exposure on t
he reproductive output of t
he copepod,
Tigriopus japonicus, using experimental data across t
hree generations. T
he model allowed us to appropriately specify t
he nonstandard statistical distribution of t
he data and account for correlations among data points. T
he approac
h ensured more robust inferences t
han standard statistical met
hods and, because of t
he model’s mec
hanistic formulation, enabled us to test more subtle
hypot
heses. We demonstrate intergeneration Cu exposure effects on bot
h components of reproductive output
howRef(this, 'ref1'); return false;" href="JavaScript:void(0);" class="ref">(1) t
he ovisac maturation rate, and
howRef(this, 'ref2'); return false;" href="JavaScript:void(0);" class="ref">(2) t
he number of nauplii per ovisac. Current and parent generation Cu exposures negatively affected current generation reproductive output. However, in terms of reproductive output, t
here was also some evidence for adaptation to parental Cu exposures, but wit
h an associated cost under Cu concentrations different from t
he parental exposure. Bayesian mixture and random-effects models present a robust framework for analyzing data of t
his kind and for better understanding c
hemical toxicity.