A novel robust multivariate regression approach to optimize multiple surfaces
RAIRO - Operations Research - Recherche Opérationnelle, Tome 52 (2018) no. 4-5, pp. 1233-1243.

Response surface methodology involves relationships between different variables, specifically experimental inputs as controllable factors, and a response or responses by incorporating uncontrollable factors named nuisance. In order to optimize these response surfaces, we should have accurate response models. A common approach to estimate a response surface is the ordinary least squares (OLS) method. Since OLS is very sensitive to outliers, some robust approaches have been discussed in the literature. Most problems face with more than one response which are mostly correlated, that are called multi-response problem. This paper presents a new approach which takes the benefits of robust multivariate regression to cope with the mentioned difficulties. After estimating accurate response surfaces, optimization phase should be applied in order to have proper combination of variables and optimum solutions. Global criterion method of multi-objective optimization has also been used to reach a compromise solution which improves all response variables simultaneously. Finally, the proposed approach is described analytically by a numerical example.

Reçu le :
Accepté le :
DOI : 10.1051/ro/2018016
Classification : 62K20
Mots-clés : Multi-response, simultaneous equation systems, multivariate robust regression, global criterion (GC) method
Moslemi, Amir 1 ; Seyyed-Esfahani, Mirmehdi 1

1
@article{RO_2018__52_4-5_1233_0,
     author = {Moslemi, Amir and Seyyed-Esfahani, Mirmehdi},
     title = {A novel robust multivariate regression approach to optimize multiple surfaces},
     journal = {RAIRO - Operations Research - Recherche Op\'erationnelle},
     pages = {1233--1243},
     publisher = {EDP-Sciences},
     volume = {52},
     number = {4-5},
     year = {2018},
     doi = {10.1051/ro/2018016},
     zbl = {1420.62351},
     mrnumber = {3880601},
     language = {en},
     url = {http://www.numdam.org/articles/10.1051/ro/2018016/}
}
TY  - JOUR
AU  - Moslemi, Amir
AU  - Seyyed-Esfahani, Mirmehdi
TI  - A novel robust multivariate regression approach to optimize multiple surfaces
JO  - RAIRO - Operations Research - Recherche Opérationnelle
PY  - 2018
SP  - 1233
EP  - 1243
VL  - 52
IS  - 4-5
PB  - EDP-Sciences
UR  - http://www.numdam.org/articles/10.1051/ro/2018016/
DO  - 10.1051/ro/2018016
LA  - en
ID  - RO_2018__52_4-5_1233_0
ER  - 
%0 Journal Article
%A Moslemi, Amir
%A Seyyed-Esfahani, Mirmehdi
%T A novel robust multivariate regression approach to optimize multiple surfaces
%J RAIRO - Operations Research - Recherche Opérationnelle
%D 2018
%P 1233-1243
%V 52
%N 4-5
%I EDP-Sciences
%U http://www.numdam.org/articles/10.1051/ro/2018016/
%R 10.1051/ro/2018016
%G en
%F RO_2018__52_4-5_1233_0
Moslemi, Amir; Seyyed-Esfahani, Mirmehdi. A novel robust multivariate regression approach to optimize multiple surfaces. RAIRO - Operations Research - Recherche Opérationnelle, Tome 52 (2018) no. 4-5, pp. 1233-1243. doi : 10.1051/ro/2018016. http://www.numdam.org/articles/10.1051/ro/2018016/

[1] T. Amemiya, The maximum likelihood and the nonlinear three-stage least squares estimator in the general nonlinear simultaneous equation model. Econometrica 45 (1977) 955–968. | DOI | MR | Zbl

[2] J. Antony, Multi-response optimization in industrial experiments using Taguchi’s quality loss function and principal component analysis. Qual. Reliab. Eng. Int. 16 (2000) 3–8. | DOI

[3] M. Bashiri and A. Moslemi, A robust moving average iterative weighting method to analyze the effect of outliers on the response surface design. Int. J. Ind. Eng. Comput. 2 (2011) 851–862.

[4] M. Bashiri and A. Moslemi, Simultaneous robust estimation of multi-response surfaces in the presence of outliers. J. Ind. Eng. Int. 9 (2013) 1–12. | DOI

[5] M. Bashiri and A. Moslemi, The analysis of residuals variation and outliers to obtain robust response surface. J. Ind. Eng. Int. 9 (2013) 1–10. | DOI

[6] R.L. Basmann, A generalized classical method of linear estimation of coefficients in a structural equation. Econometrica 25 (1957) 77–83. | DOI | MR | Zbl

[7] C.H. Chiao and M. Hamada, Analyzing experiments with correlated multiple responses. J. Q. Technol. 33 (2001) 451. | DOI

[8] D.J. Cummins and C.W. Andrews, Iteratively reweighted partial least squares: a performance analysis by Monte Carlo simulation. J. Chem. 9 (1995) 489–507. | DOI

[9] Y. Donoso and R. Fabregat, Multi-Objective Optimization in Computer Networks Using Metaheuristics. Auerbach Publications, Boca Raton (2007). | Zbl

[10] L.P. Hansen, Large sample properties of generalized method of moment’s estimators. Econometrica 50 (1982) 1029–1054. | DOI | MR | Zbl

[11] T.H. Hejazi, M. Bashiri, J.A. Díaz-García and K. Noghondarian, Optimization of probabilistic multiple response surfaces. Appl. Math. Model. 36 (2012) 1275–1285. | DOI | MR | Zbl

[12] P.J. Huber, Robust Statistics. John Wiley & Sons, New York (1981). | DOI | MR | Zbl

[13] E. Hund,D.L. Massart and J. Smeyers-Verbeke, Robust regression and outlier detection in the evaluation of robustness tests with different experimental designs. Anal. Chim. Acta 463 (2002) 53–73. | DOI

[14] R.B. Kazemzadeh, M. Bashiri, A.C. Atkinson and R. Noorossana, A general framework for multiresponse optimization problems based on goal programming. Eur. J. Oper. Res. 189 (2008) 421–429. | DOI | MR | Zbl

[15] R. Koenker and S. Portnoy, L-estimation for linear models. J. Am. Stat. Assoc. 82 (1987) 851–857. | MR | Zbl

[16] R. Maronna and S. Morgenthaler, Robust regression through robust covariances. Commun. Stat. Theory Methods 15 (1986) 1347–1365. | DOI | MR | Zbl

[17] R.A.R.D.Maronna, D. Martin and V. Yohai, Robust Statistics. John Wiley & Sons, Chichester (2006) 978. | MR | Zbl

[18] D.C. Montgomery, Design and Analysis of Experiments, 6th edn. John Wiley & Sons, Hoboken (2005). | MR

[19] S. Morgenthaler and M.M. Schumacher, Robust analysis of a response surface design. Chem. Intel. Lab. Syst. 47 (1999) 127–141. | DOI

[20] J.S. Ribeiro, R.F. Teófilo, F. Augusto and M.M.C. Ferreira, Simultaneous optimization of the microextraction of coffee volatiles using response surface methodology and principal component analysis. Chem. Intel. Lab. Syst. 102 (2010) 45–52. | DOI

[21] P. Rousseeuw, S. Van Aelst, K. Van Driessen and J. Agullo, Robust multivariate regression. Technometrics 46 (2004) 293–305. | DOI | MR

[22] A. Salmasnia, R.B. Kazemzadeh, M. Seyyed-Esfahani and T.H. Hejazi, Multiple response surface optimization with correlated data. Int. J. Adv. Manuf. Technol. 64 (2013) 841–855. | DOI

[23] H.K. Shah, D.C. Montgomery and W.M. Carlyle, Response surface modeling and optimization in multiresponse experiments using seemingly unrelated regressions. Qual. Eng. 16 (2004) 387–397. | DOI

[24] C.H. Wang, Dynamic multi-response optimization using principal component analysis and multiple criteria evaluation of the grey relation model. Int. J. Adv. Manuf. Technol. 32 (2007) 617–624. | DOI

[25] D.P. Wiens and E.K. Wu, A comparative study of robust designs for M-estimated regression models. Comput. Stat. Data Anal. 54 (2010) 1683–1695. | DOI | MR | Zbl

[26] A. Zellner, An efficient method of estimating seemingly unrelated regressions and tests for aggregation bias. J. Am. Stat. Assoc. 57 (1962) 348–368. | DOI | MR | Zbl

[27] A. Zellner and H. Theil, Three-stage least squares: simultaneous estimation of simultaneous equations. Econometrica 30 (1962) 54–78. | DOI | MR | Zbl

[28] C.T. Su and L.I. Tong, Multi-response robust design by principal component analysis. Total Quality Manage. 8 (199) 409–416.

[29] L.I. Tong, W. Chung-Ho and C. Hung-Cheng, Optimization of multiple responses using principal component analysis and technique for order preference by similarity to ideal solution. Int. J. Adv. Manuf. Technol. 27 (2005) 407–414. | DOI

Cité par Sources :