S. Pozuelo Campos, M. Amo Salas, V. M. Casero Alonso
Toxicological tests are widely used to study toxicity in aquatic environments. Reproduction is a possible endpoint of this type of experiment, whose response variable is given by counts. There is literature about the suitable probability distribution to be used for analyzing these data. In the theory of optimal experimental design, the assumption of this probability distribution is essential, and when this assumption is not adequate, there may be a loss of efficiency in the design obtained. The main objective of this study is to propose robust designs when there is uncertainty about the probability distribution of the response variable. We introduce and compare three different strategies for attaining this goal and they are applied to toxicological tests based on Ceriodaphnia dubia and Lemna minor. In addition, a simulation study is performed to test the estimation properties of the robust designs obtained.
Keywords: D-optimality, Elemental Information Matrix, Exponential Family Distribution, Linear Logistic model.
Scheduled
GT07 Design of Experiments II
June 8, 2022 4:00 PM
Conference hall