Optimal Design For Additive Partially Nonlinear Models
نویسندگان
چکیده
We develop optimal design theory for additive partially nonlinear regression models, and show that D-optimal designs can be found as the products of the corresponding D-optimal designs in one dimension. For partially nonlinear models, D-optimal designs depend on the unknown nonlinear model parameters, and misspeci_cations of these parameters can lead to poor designs. Hence we generalise our results to parameter robust optimality criteria, namely Bayesian and standardised maximin D-optimality. A su_cient condition under which analogous results hold for Ds-optimality is derived to accommodate situations in which only a subset of the model parameters is of interest. To facilitate prediction of the response at unobserved locations, we prove similar results for Q-optimality in the class of all product designs. The usefulness of this approach is demonstrated through an application from the automotive industry where optimal designs for least squares regression splines are determined and compared with designs commonly used in practice. Optimal design for additive partially nonlinear models Stefanie Biedermann University of Southampton School of Mathematics Southampton SO17 1BJ UK email: [email protected] Holger Dette Ruhr-Universität Bochum Fakultät für Mathematik 44780 Bochum Germany email: [email protected] David C. Woods University of Southampton Statistical Sciences Research Institute Southampton SO17 1BJ UK email: [email protected]
منابع مشابه
Presentation of quasi-linear piecewise selected models simultaneously with designing of bump-less optimal robust controller for nonlinear vibration control of composite plates
The idea of using quasi-linear piecewise models has been established on the decomposition of complicated nonlinear systems, simultaneously designing with local controllers. Since the proper performance and the final system close loop stability are vital in multi-model controllers designing, the main problem in multi-model controllers is the number of the local models and their position not payi...
متن کاملSparse Partially Linear Additive Models
The generalized partially linear additive model (GPLAM) is a flexible and interpretable approach to building predictive models. It combines features in an additive manner, allowing them to have either a linear or nonlinear effect on the response. However, the assignment of features to the linear and nonlinear groups is typically assumed known. Thus, to make a GPLAM a viable approach in situatio...
متن کاملFriction Compensation for Dynamic and Static Models Using Nonlinear Adaptive Optimal Technique
Friction is a nonlinear phenomenon which has destructive effects on performance of control systems. To obviate these effects, friction compensation is an effectual solution. In this paper, an adaptive technique is proposed in order to eliminate limit cycles as one of the undesired behaviors due to presence of friction in control systems which happen frequently. The proposed approach works for n...
متن کاملOptimal Design of Geometrically Nonlinear Structures Under a Stability Constraint
This paper suggests an optimization-based methodology for the design of minimum weight structures with kinematic nonlinear behavior. Attention is focused on three-dimensional reticulated structures idealized with beam elements under proportional static loadings. The algorithm used for optimization is based on a classical optimality criterion approach using an active-set strategy for extreme lim...
متن کاملANT COLONY ALGORITHMS FOR NONLINEAR ANALYSIS AND OPTIMAL DESIGN OF STRUCTURES
In this paper nonlinear analysis of structures are performed considering material and geometric nonlinearity using force method and energy concepts. For this purpose, the complementary energy of the structure is minimized using ant colony algorithms. Considering the energy term next to the weight of the structure, optimal design of structures is performed. The first part of this paper contains ...
متن کامل