Robust designs for discriminating between trigonometric regression models

Authors

  • Viatcheslav B. Melas
  • Petr V. Shpilev
  • Olga Yu. Nikolaeva

Abstract

Данная работа посвящена задаче построения робастных Т-оптимальных планов для дискриминации двух тригонометрических регрессионных моделей, отличающихся не более, чем тремя старшими членами. Для решения этой задачи в работе используется байесовский и стандартизированный максиминный подходы. В ряде специальных случаев робастные Т-оптимальные дискриминационные планы найдены в явном виде. В общем случае, в силу высокой сложности оптимизационной задачи, соответствующий план нелегко найти в явном виде, но он может быть найден численно. Результаты проиллюстрированы примерами.

Downloads

Download data is not yet available.

References

1. Atkinson A., Bogacka B., Bogacki M. D- and t-optimum designs for the kinetics of a reversiblechemical reaction // Chemometrics and Intelligent Laboratory Systems. 1998. Vol.43. P.185–198.

2. Asprey S., Macchietto S. Statistical tools for optimal dynamic model building // Computersand Chemical Engineering. 2000. Vol.24. P.1261–1267.

3. Ucinski D., Bogacka B. T-optimum designs for discrimination between two multiresponse dy-namic models // Journal of the Royal Statistical Society. Ser. B. 2005. Vol.67. P.3–18.

4. Atkinson A.C., Fedorov V.V. The designs of experiments for discriminating between two rivalmodels // Biometrika. 1975. Vol.62. P.57–70.

5. Atkinson A.C., Fedorov V.V. Optimal design: Experiments for discriminating between severalmodels // Biometrika. 1975. Vol.62. P.289–303.

6. WiensD.P. Robust discrimination designs,with Matlab code //Journal of theRoyal StatisticalSociety. Ser. B. 2009. Vol.71. P.805–829.

7. Tommasi C., Lop´ ez-Fidalgo J. Bayesian optimum designs for discriminating between modelswith any distribution // Computational Statistics & Data Analysis. 2010. Vol.54, no.1. P.143–150.

8. Waterhouse T., Woods D., Eccleston J., Lewis S. Design selection criteria for discrimina-tion/estimation for nested models and a binomial response // Journal of Statistical Planning and Infer-ence. 2008. Vol.138. P.132–144.

9. Dette H., Melas V.B., Shpilev P. T-optimal designs for discrimination between two polynomialmodels // Annals of Statistics. 2012. Vol.40, no.1. P.188–205.

10. Dette H., Melas V.B., Shpilev P. T-optimal discriminating designs for fourier regression models.// Computational Statistics and Data Analysis. 2017. Vol.113. P.196–206.

11. Dette H., Melas V.B., Shpilev P. Robust T-optimal discriminating designs // Annals of Statis-tics. 2013. Vol.41, no.1. P.1693–1715.

12. Gaffke N. Further characterizations of designoptimalityand admissibilityforpartial parameterestimation on linear regression // Annals of Statistics. 1987. Vol.15, no.3. P.942–957.

13. Pukelsheim F. Optimal Design of Experiments. Philadelphia: SIAM, 2006.

14. Mueller C., Pazman A. Applications of necessary and sufficient conditions formaximinefficientdesigns // Metrika. 1998. Vol.48. P.1–19.

15. Dette H., Neugebauer H. Bayesian optimal one point designs for one parameternon linear models// Journal of Statistical Planning and Inference. 1996. Vol.52. P.17–31.

16. Dette H., Neugebauer H. Bayesian d-optimal designs for exponential regression models //Journal of Statistical Planning and Inference. 1997. Vol.60. P.331–349.

17. Dette H. Designing experiments with respect to “standardized” optimality criteria // Journalof the Royal Statistical Society. 1997. Vol.59. P.97–110.

18. Dette H., Melas V.B., Shpilev P. Optimal designs for trigonometric regression models //Journal of Statistical Planning and Inference. 2011. Vol.141, no.3. P.1343–1353.

Downloads

Published

2020-08-17

How to Cite

Melas, V. B., Shpilev, P. V., & Nikolaeva, O. Y. (2020). Robust designs for discriminating between trigonometric regression models. Vestnik of Saint Petersburg University. Mathematics. Mechanics. Astronomy, 6(1), 98–109. Retrieved from https://math-mech-astr-journal.spbu.ru/article/view/8434

Issue

Vol. 6 No. 1 (2019)

Section

Mathematics

License

Articles of "Vestnik of Saint Petersburg University. Mathematics. Mechanics. Astronomy" are open access distributed under the terms of the License Agreement with Saint Petersburg State University, which permits to the authors unrestricted distribution and self-archiving free of charge.