Parametric estimation of P(X > Y) for normal distributions in the context of probabilistic environmental risk assessment

摘要: Estimating the risk, P(X > Y), in probabilistic environmental risk assessment of nanoparticles is a problem when confronted by potentially small risks and sample sizes exposure concentration X and/or effect Y. This illustrated motivating case study aquatic nano-Ag. A non-parametric estimator based on data alone not sufficient as it limited size. In this paper, we investigate maximum gain possible making strong parametric assumptions opposed to no at all. We compare likelihood Bayesian estimators with influence size (interval) via simulation. found that enable us estimate bound for smaller risks. Also, outperforms terms coverage interval lengths is, therefore, preferred our study.