←Back
165 – New Developments and Applications in Design of Experiments
Nonlinear Quantile Regression Design
Sponsor: Section on Physical and Engineering Sciences
Keywords: Minimax design, Asymptotic mean squared error, Genetic algorithm, Regression quantiles, Uniformity
Linglong Kong
University of Alberta
Douglas Wiens
University of Alberta
We give methods for the construction of designs for regression models, when the purpose of the investigation is the estimation of the conditional quantile function and the estimation method is quantile regression. The designs are robust against misspecified response functions, and against unanticipated heteroscedasticity. Our methods, previously developed for approximate linear models, are modified so as to apply to nonlinear responses. The results will be illustrated in a dose response example.