T-optimal designs for discrimination between two polynomial models

DOI10.1214/11-AOS956MaRDI QIDQ450028zbMATH OpenOpenAlexFDO

Authors Holger Dette, Viatcheslav B. Melas, Petr Shpilev

Publication date 3 September 2012

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1205.6283, https://projecteuclid.org/euclid.aos/1331830779

zbMATH Keywords

goodness-of-fit testsmodel uncertaintyChebyshev polynomialsuniform approximation

Mathematics Subject Classification ID

Optimal statistical designs (62K05)

Abstract: This paper is devoted to the explicit construction of optimal designs for discrimination between two polynomial regression models of degree $n-2$ and $n$. In a fundamental paper, Atkinson and Fedorov [Biometrika 62 (1975a) 57--70] proposed the $T$-optimality criterion for this purpose. Recently, Atkinson [MODA 9, Advances in Model-Oriented Design and Analysis (2010) 9--16] determined $T$-optimal designs for polynomials up to degree 6 numerically and based on these results he conjectured that the support points of the optimal design are cosines of the angles that divide half of the circle into equal parts if the coefficient of $x^{n-1}$ in the polynomial of larger degree vanishes. In the present paper we give a strong justification of the conjecture and determine all $T$-optimal designs explicitly for any degree $ninmathbbN$. In particular, we show that there exists a one-dimensional class of $T$-optimal designs. Moreover, we also present a generalization to the case when the ratio between the coefficients of $x^{n-1}$ and $x^n$ is smaller than a certain critical value. Because of the complexity of the optimization problem, $T$-optimal designs have only been determined numerically so far, and this paper provides the first explicit solution of the $T$-optimal design problem since its introduction by Atkinson and Fedorov [Biometrika 62 (1975a) 57--70]. Finally, for the remaining cases (where the ratio of coefficients is larger than the critical value), we propose a numerical procedure to calculate the $T$-optimal designs. The results are also illustrated in an example.

Recommendations

• T-optimal designs for discrimination between rational and polynomial models
• Optimal discrimination designs
• Robust \(T\)-optimal discriminating designs
• Optimal discriminating designs for several competing regression models
• \(T\)-optimal discriminating designs for Fourier regression models

Cites work

• scientific article; zbMATH DE number 3165668 (Why is no real title available?)
• scientific article; zbMATH DE number 4213265 (Why is no real title available?)
• scientific article; zbMATH DE number 3734990 (Why is no real title available?)
• scientific article; zbMATH DE number 3770795 (Why is no real title available?)
• scientific article; zbMATH DE number 3477793 (Why is no real title available?)
• scientific article; zbMATH DE number 3502650 (Why is no real title available?)
• scientific article; zbMATH DE number 1271146 (Why is no real title available?)
• scientific article; zbMATH DE number 1086072 (Why is no real title available?)
• T-Optimum Designs for Discrimination Between Two Multiresponse Dynamic Models
• A Review of Experimental Design Procedures for Regression Model Discrimination
• Bayesian experimental design: A review
• Bayesian optimum designs for discriminating between models with any distribution
• Discrimination designs for polynomial regression on compact intervals
• Duality of optimal designs for model discrimination and parameter estimation
• Functional approach to optimal experimental design.
• General equivalence theory for optimum designs (approximate theory)
• Locally Optimal Designs for Estimating Parameters
• On the interaction of electromagnetic waves with charged particles and on the oscillations of the electronic plasma
• Optimal Experimental Design for Polynomial Regression
• Optimal designs for estimating individual coefficients in polynomial regression -- a functional approach
• Optimal designs for identifying the degree of a polynomial regression
• Optimal designs for the identification of the order of a Fourier regression
• Optimal discrimination designs
• Robust discrimination designs
• Robustness of design for the testing of lack of fit and for estimation in binary response models
• Some Robust-Type D-Optimal Designs in Polynomial Regression
• The design of experiments for discriminating between two rival models
• \(D_s\)-optimal designs for polynomial regression using continued fractions

Cited in

(15)

• \(T\)-optimal discriminating designs for Fourier regression models
• Bayesian \(T\)-optimal discriminating designs
• T-optimal designs for multi-factor polynomial regression models via a semidefinite relaxation method
• \(T\)-optimal designs for discrimination between rational and polynomial models
• Optimal discriminating designs for several competing regression models
• On standardized maximin designs for discrimination between two polynomial models
• Block designs robust against the presence of positional effects
• Robust \(T\)-optimal discriminating designs
• Optimum designs for the equality of parameters in enzyme inhibition kinetic models
• A semi-infinite programming based algorithm for determining T-optimum designs for model discrimination
• KL-optimum designs: theoretical properties and practical computation
• Robust designs for discriminating between trigonometric regression models
• Ensuring balance through optimal allocation of experimental units with known categorical covariates into two treatments
• \(L\)-optimal designs for a trigonometric Fourier regression model with no intercept
• Quasi-Newton algorithm for optimal approximate linear regression design: optimization in matrix space

This page was built for publication: \(T\)-optimal designs for discrimination between two polynomial models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q450028)