Abstract
In this paper the non-linear problem is discussed, for point and interval computational estimation. For the interval estimation an adjusted formulation is discussed due to Beale’s measure of non-linearity. The non-linear experimental design problem is regarded when the errors of observations are assumed i.i.d. and normally distributed as usually. The sequential approach is adopted. The average-per-observation information matrix is adopted to the developed theoretical approach. Different applications are discussed and we provide evidence that the sequential approach might be the panacea for solving a non-linear optimal experimental design problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
D.M. Bates, D.G. Watts, Non-linear Regression Analysis and its Applications (John Wiley and Sons, Hoboken, 1998)
E.M.L. Beale, Confidence regions in non-linear estimation. J. R. Stat. Soc. Ser. B Methodol. 22, 41–88 (1960)
D.S. Borowiak, Model Discrimination in Nonlinear Regression Models (Marcel Dekker, New York, 1989)
P. Chadhuri, P.A. Mykland, Nonlinear experiments: optimal design and inference based on likelihood. J. Am. Stat. Assoc. 88, 538–546 (1995)
P. Chadhuri, P.A. Mykland, In efficient designing of nonlinear experiments. Statistica Sinica 5, 421–440 (1995)
D.J. Finney, Statistical Methods in Biological Assay (C. Griffin and Co. Ltd., Glasgow, 1978)
I. Ford, C.P. Kitsos, D.M. Titterington, Recent advances in non-linear experimental design. Technometrics 31, 49–60 (1989)
R.J. Jennrich, Asymptotic properties of non-linear least squares estimators. Ann. Math. Stat. 40, 633–643 (1969)
C.P. Kitsos, Design and Inference for the Nonlinear Problems. Ph.D. Thesis. Glasgow (1986)
C.P. Kitsos, Fully-sequential procedures in nonlinear design problems. Comp. Stat. Data Anal. 8, 13–19 (1989)
C.P. Kitsos, Adopting sequential procedures for biological experiments. In: MODA3 (Model Oriented Data Analysis), ed. by W.G. Muller, H.P. Wynn, A.A. Zhigliavsky (Physica-Verlag, Heidelberg, 1992), pp. 3–9
C.P. Kitsos, On the support points of D-optimal nonlinear experiment design for chemical kinetics. In: Model Oriented Data Analysis, ed. by C. Kitsos, W. Mueller (Physica-Verlag, Heidelberg, 1995), pp. 71–76
C.P. Kitsos, The role of covariates in experimental carcinogenesis. Biomed. Lett. 35, 95–106 (1998)
C.P. Kitsos, Optimal designs for estimating the percentiles of the risk in multistage models in carcinogenesis. Biomet. J. 41, 33–43 (1999)
C.P. Kitsos, Design aspects for the Michaelis-Menten model. Biomet Lett. 38, 53–66 (2001)
C.P. Kitsos, Optimal design for bioassays in carcinogenesis. In: Quantitative Methods for Cancer and Human Health Risk Assessment, ed. by L. Edler, C. Kitsos (Wiley, Hoboken, 2005), pp. 267–279
C.P. Kitsos, L. Edler, Cancer risk assessment for mixtures. In: Quantitative Methods for Cancer and Human Health Risk Assessment, ed. by L. Edler, C. Kitsos (Wiley, Hoboken, 2005), pp. 283–298
C.P. Kitsos, K.G. Kolovos, A compilation of the D-optimal designs in chemical kinetics. Chem. Eng. Commun. 200(2), 185–204 (2013). http://dx.doi.org/10.1080/00986445.2012.699481
C.P. Kitsos, K.G. Kolovos, Optimal Calibration Procedures for Calibrating the pH Meters (Lambert Academic Publishing, Saarbrücken, 2010). ISBN: 978-3-8433-5286-4
C.P. Kitsos, Ch.H. Muller, Robust estimation of non-linear aspects. In: MODA4 (Model Oriented Data Analysis), ed. by C. Kitsos, W. Muller (Physica, Heidelberg, 1995), pp. 71–76
C.P. Kitsos, Ch.H. Muller, Robust linear calibration. Statistics 27, 93–103 (1995)
C.P. Kitsos, D.M. Titterington, B. Torsney, An optimal design problem in rhythmometry. Biometrics 44, 657–671 (1988)
P. McCallagh, J. Nelder, Generalized Linear Models (Chapman and Hall, London, 1989)
J.M. Ortega, W.C. Pheinfold, Iterative Solution of Nonlinear Equation in Several Variables (Academic, London, 1970)
F. Pukelsheim, Optimal Design of Experiments (John Wiley, Hoboken, 1993)
H. Robbins, S. Monro, A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)
D.J. Sakrison, Efficient recursive estimation: application to estimating the parameters of a covariance function. Int. J. Eng. Sci. 3, 461–483 (1965)
G.A.F. Seber, C.J. Wild, Nonlinear Regression (John Wiley and Sons, Hoboken, 1989)
M.J. Silvapulle, On the existence of the maximum likelihood estimators for the binomial response models. J. R. Stat. Soc. Ser. B Methodol. 43, 310–313 (1981)
S.D. Silvey, Optimal Design (Chapman and Hall, London, 1980)
R.R. Sitter, B. Torsney, D-optimal designs for generalized linear models. In: MODA4 (Model Oriented Data Analysis), ed. by C. Kitsos, W. Muller (Physica, Heidelberg, 1995), pp. 87–102
J. Wolfowitz, On the stochastic approximation method of Robbins and Monro. Ann. Math. Stat. 23, 457–461 (1973)
W. Wosniok, C. Kitsos, K. Watanabe, Statistical issues in the application of multistage and biologically based models. In: Prospective on Biologically Based Cancer Risk Assessment. NATO Pilot Study Publication ed. by V.J. Cogliano, G.E. Luebeck, G.A. Zapponi (Plenum Publishing Co., New York, 1998)
C.F.J. Wu, H.P. Wynn, The convergence of general step – length algorithms for regular optimum design criteria. Ann. Stat. 6, 1273–1285 (1978)
V. Zarikas, V. Gikas, C.P. Kitsos, Evaluation of the optimal design “cosinor model” for enhancing the potential of robotic theodolite kinematic observation. Measurement 43(10), 1416–1424 (2010). http://dx.doi.org/10.1016/j.measurement.2010.08.006
Acknowledgements
This research is based on the partial results of the fund by FCT—Fundação para a Ciência e a Tecnologia, Portugal, through the project UID/MAT/00006/2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
1. Local Selection Criteria for NLM
-
C1: Mallow’s C p-statistic \(C_p(\theta )=(\frac {RSS}{s^2})-n+2p\)
-
C2: Akaike’s criterion \(AC(\theta )=nln(\frac {RSS}{n}+\frac {n(n+p)}{n-p-2}\)
-
C3: Weighted \(WRSS(\theta )=\sum _{i}[\frac {(y_i-\hat {y}_i)^2}{1-W_i}]\)
-
C4: p—Weighted \(WRSS_p(\theta )=\frac {WRSS(\theta )}{s^2}-n+2p\)
-
C5: B-criterion \(B_{max}=\frac {RSS}{s^2}-(n-p)+3s^2B\)
with W i as defined in (9).
2. Proof of Proposition 5
Indeed from (19) for the true 𝜗, 𝜗 t and the estimate \(\hat {\vartheta }\) it holds for the corresponding sum of squares:
from ([9], pg.81) with B as in (26).
But B is as in [23] and we extend it to (28). We approximate B 0 by the value of the intrinsic curvature of the model γ max. This curvature provides a measure to “how good is the target-plane approximation,” in other words “how far from linear” is the model. But there is an upper bound of γ max, see ([28], pg.135), namely
So, with p = 1, it is \(F(a;1;n-p)=t_{n-p}^2\), i.e. \(\gamma _0=\frac {1}{2}t(a;n-1)\), that is, \(B=1+\frac {n}{n+1}B_0<1+\frac {n}{n-1}\frac {1}{2}t(a;n-1)\approx 2.2:=B_k\).
When p = 2, recall (26) and (30):
With p = 3 similar calculations provide evidence that \(B_k=1+0.41\frac {n}{n-3}\) approximating \(\sqrt {F}\) by a rough approximation 2 with n > 9 at a = 0.05.
Also with p ≥ 4 considering (29) and (30) the last part of (28) is defined, q.e.d.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kitsos, C.P., Oliveira, A. (2020). On the Computational Methods in Non-linear Design of Experiments. In: Daras, N., Rassias, T. (eds) Computational Mathematics and Variational Analysis. Springer Optimization and Its Applications, vol 159. Springer, Cham. https://doi.org/10.1007/978-3-030-44625-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-44625-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44624-6
Online ISBN: 978-3-030-44625-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)