Interval estimation of the \(ED_{50}\) when a logistic dose-response curve is incorrectly assumed (Q5941339)

For a correctly assumed logistic dose-response curve, a number of authors have considered various interval estimation methods for the median effective dose \((ED_{50}).\) We look at the performance of four large sample parametric methods and four bootstrap resampling approaches for the problem of constructing confidence intervals of the \(ED_{50}\) and investigate the robustness of these methods when a logistic dose-response curve is incorrectly assumed. The underlying true dose-response curve studied is, respectively, either the probit model, the cubic logistic model or the asymmetric Aranda-Ordaz model.