Skip to content
BY 4.0 license Open Access Published by De Gruyter Open Access October 27, 2020

Detecting and modeling critical dependence structures between random inputs of computer models

Nazih Benoumechiara , Nicolas Bousquet EMAIL logo , Bertrand Michel and Philippe Saint-Pierre
From the journal Dependence Modeling

Abstract

Uncertain information on input parameters of computer models is usually modeled by considering these parameters as random, and described by marginal distributions and a dependence structure of these variables. In numerous real-world applications, while information is mainly provided by marginal distributions, typically from samples, little is really known on the dependence structure itself. Faced with this problem of incomplete or missing information, risk studies that make use of these computer models are often conducted by considering independence of input variables, at the risk of including irrelevant situations. This approach is especially used when reliability functions are considered as black-box models. Such analyses remain weakened in absence of in-depth model exploration, at the possible price of a strong risk misestimation. Considering the frequent case where the reliability output is a quantile, this article provides a methodology to improve risk assessment, by exploring a set of pessimistic dependencies using a copula-based strategy. In dimension greater than two, a greedy algorithm is provided to build input regular vine copulas reaching a minimum quantile to which a reliability admissible limit value can be compared, by selecting pairwise components of sensitive influence on the result. The strategy is tested over toy models and a real industrial case-study. The results highlight that current approaches can provide non-conservative results.

MSC 2010: 62G07; 62G32; 62P30; 62H20

References

[1] Aas, K., C. Czado, A. Frigessi and H. Bakken (2009). Pair-copula constructions of multiple dependence. Insurance Math. Econom. 44(2), 182–198.10.1016/j.insmatheco.2007.02.001Search in Google Scholar

[2] Agrawal, S., Y. Ding, A. Saberi and Y. Ye (2012). Price of correlations in stochastic optimization. Oper. Res. 60(1), 150–162.10.1287/opre.1110.1011Search in Google Scholar

[3] Bayarri, M., J. O. Berger, R. Paulo, J. Sacks, J. Cafeo, J. Cavendish, C. Lin and J. Tu (2007). A framework for validation of computer models. Technometrics 49(2), 138–154.10.1198/004017007000000092Search in Google Scholar

[4] Beaudoin, D. and L. Lakhal-Chaieb (2008). Archimedean copula model selection under dependent truncation. Stat. Med. 27(22), 4440–4454.10.1002/sim.3316Search in Google Scholar PubMed

[5] Bedford, T., J. Quigley and L. Walls (2006). Expert elicitation for reliable system design. Statist. Sci. 21(4), 428–450.10.1214/088342306000000510Search in Google Scholar

[6] Bedford, T. and R. M. Cooke (2001). Probability density decomposition for conditionally dependent random variables modeled by vines. Ann. Math. Artif. Intell. 32(1), 245–268.10.1023/A:1016725902970Search in Google Scholar

[7] Bedford, T. and R. M. Cooke (2001). Vines: a new graphical model for dependent random variables. Ann. Statist. 30(4), 1031–1068.Search in Google Scholar

[8] Benoumechiara N. (2017). dep-impact: A python package for conservative estimation of an output quantity of interest in reliabilty problems. Available at https://github.com/nazben/dep-impact.Search in Google Scholar

[9] Bobkov,S. and M. Ledoux (2019). One-dimensional Empirical Measures, Order Statistics, and Kantorovich Transport Distances. American Mathematical Society, Providence.10.1090/memo/1259Search in Google Scholar

[10] Brabbia C., M.E. Conti and E. Tiezzi (2006). Management of Natural Ressources, Sustainable Development and Ecological Hazards. WIT Press, Southampton.Search in Google Scholar

[11] Brechmann E. C., K. Aas and C. Czado (2012). Truncated regular vines in high dimensions with application to financial data. Canad. J. Statist. 40(1), 68–85.10.1002/cjs.10141Search in Google Scholar

[12] Chazal, F., P. Massart and B. Michel (2016). Rates of convergence for robust geometric inference. Electron. J. Stat. 10(2), 2243–2286.10.1214/16-EJS1161Search in Google Scholar

[13] Cherubini, U., E. Luciano, W. Vecchiato (2004). Copula Methods in Finance.Wiley, Chichester.10.1002/9781118673331Search in Google Scholar

[14] Clemen, R. T. and T. Reilly (1999). Correlations and copulas for decision and risk analysis. Manag. Sci. 45(2), 208–224.10.1287/mnsc.45.2.208Search in Google Scholar

[15] National Research Council (2012). Assessing the Reliability of Complex Models: Mathematical and Statistical Foundations of Verification, Validation and Uncertainty Quantification. National Academies Press, Washington.Search in Google Scholar

[16] Csorgo M. (1983). Quantile Processes with Statistical Applications. SIAM, Philadelphia PA.Search in Google Scholar

[17] Czado C. (2010). Pair-copula constructions of multivariate copulas. In P. Jaworski, F. Durante, W. K. Härdle, T. Rychlik (Eds.), Copula Theory and its Applications, pp. 93–109. Springer, New York.10.1007/978-3-642-12465-5_4Search in Google Scholar

[18] de Rocquigny, E., N. Devictor and S. Tarantola (2008). Uncertainty in Industrial Practice: a Guide to Quantitative Uncertainty Management. John Wiley & Sons, Chichester.10.1002/9780470770733Search in Google Scholar

[19] Demarta, S. and A. J. McNeil (2005). The t copula and related copulas. Int. Stat. Rev. 73(1), 111–129.10.1111/j.1751-5823.2005.tb00254.xSearch in Google Scholar

[20] Dissmann, J., E. C. Brechmann, C. Czado and D. Kurowicka (2013). Selecting and estimating regular vine copulae and application to financial returns. Comput. Statist. Data Anal. 59, 52–69.10.1016/j.csda.2012.08.010Search in Google Scholar

[21] Dvoretzky, A., J. Kiefer and J. Wolfowitz (1956). Asymptotic minimax character of the sample distribution function and of the classical multinomial estimator. Ann. Math. Statist. 27(3), 642–669.10.1214/aoms/1177728174Search in Google Scholar

[22] Echard, B., N. Gayton and M. Lemaire (2011). AK-MCS: an active learning reliability method combining kriging and Monte Carlo simulation. Struct. Saf. 33(2), 145–154.10.1016/j.strusafe.2011.01.002Search in Google Scholar

[23] Echard, B., N. Gayton, M. Lemaire, N. Relun (2013). A combined importance sampling and kriging reliability method for small failure probabilities with time-demanding numerical models. Reliab. Eng. Syst. Saf. 111, 232–240.10.1016/j.ress.2012.10.008Search in Google Scholar

[24] Embrechts, P., A. J. McNeil and D. Straumann (2002). Correlation and dependence in risk management: properties and pitfalls. In M. A. H. Dempster (Ed.), Risk Management: Value at Risk and Beyond, pp. 176–223. Cambridge University Press.10.1017/CBO9780511615337.008Search in Google Scholar

[25] Estes, A. C. and D. M. Frangopol (2005). Load rating versus reliability analysis. J. Struct. Eng. 131(5), 843–847.10.1061/(ASCE)0733-9445(2005)131:5(843)Search in Google Scholar

[26] Evans, L. C. and R. F. Gariepyl (2015). Measure Theory and Fine Properties of Function. CRC Press, Boca Raton FL.Search in Google Scholar

[27] Fréchet M. (1951). Sur les tableaux de correlation dont les marges sont données. Ann. Univ. Lyon 9, 53–77.Search in Google Scholar

[28] Frees, E. W. and E. A. Valdez (1998). Understanding relationships using copulas. N. Am. Actuar. J. 2(1), 1-25.10.1080/10920277.1998.10595667Search in Google Scholar

[29] Goda K. (2010). Statistical modeling of joint probability distribution using copula: application to peak and permanent displacement seismic demands. Struct. Saf. 32(2), 112–123.10.1016/j.strusafe.2009.09.003Search in Google Scholar

[30] Grigoriu, M. and C. Turkstra (1979). Safety of structural systems with correlated resistances. Appl. Math. Model. 3(2), 130–136.10.1016/0307-904X(79)90040-4Search in Google Scholar

[31] Gruber, L. and C. Czado (2015). Sequential bayesian model selection of regular vine copulas. Bayesian Anal. 10(4), 937–963.10.1214/14-BA930Search in Google Scholar

[32] Guntenspergen G. R. (2014). Application of Threshold Concepts in Natural Resource Decision Making. Springer, New York.10.1007/978-1-4899-8041-0Search in Google Scholar

[33] Haff. I. H. (2016). How to select a good vine. International FocuStat Workshop on Focused Information Criteria and Related Themes. Available at https://www.mn.uio.no/math/english/research/projects/focustat/workshops%20and%20conference/workshop-2016/vineselection.pdfSearch in Google Scholar

[34] Helton J. C. (2011). Quantification of margins and uncertainties: conceptual and computational basis. Reliab. Eng. Syst. Saf. 96(9), 976–1013.10.1016/j.ress.2011.03.017Search in Google Scholar

[35] Hoeffding W.(1940). Scale-invariant correlation theory. In N.I. Fisher and P. K. Sen (Eds.), The Collected Works of Wassily Hoeffding, pp. 57–107. Springer, New York.Search in Google Scholar

[36] Iooss, B. and P. Lemaître (2015). A review on global sensitivity analysis methods. In G. Dellino and C. Meloni (Eds.), Uncertainty Management in Simulation-Optimization of Complex Systems, pp. 101–122, Springer, Boston.10.1007/978-1-4899-7547-8_5Search in Google Scholar

[37] Jiang, C., W. Zhang, X. Han, B. Y. Ni and L. J. Song (2015). A vine-copula-based reliability analysis method for structures with multidimensional correlation. J. Mech. Des. 137(6), 13 pages.10.1115/1.4030179Search in Google Scholar

[38] Joe H. (1994). Multivariate extreme-value distributions with applications to environmental data. Canad. J. Statist. 22(1), 47–64.10.2307/3315822Search in Google Scholar

[39] Joe H. (1996). Families of m-variate distributions with given margins and m (m-1)/2 bivariate dependence parameters. In L. Rüschendorf, B. Schweizer and M. D.Taylor (Eds.), Distributions with Fixed Marginals and Related Topics, pp. 120–141. IMS, Hayward.10.1214/lnms/1215452614Search in Google Scholar

[40] Karlin, S., K. Arrow and H. Scarf (1958). A min-max solution of an inventory problem. In J. K. Arrow, S. Karlin and H. Scarf (Eds.), Studies in the International Theory of Inventory and Productions, pp. 201–209. Standford University Press, Redwood.Search in Google Scholar

[41] Kendall M. G. (1938). A new measure of rank correlation. Biometrika. 30(1/2), 81–93.10.1093/biomet/30.1-2.81Search in Google Scholar

[42] Kurowicka D. (2011). Optimal truncation of vines. In D. Kurowicka and H. Joe (Eds.), Dependence Modeling: Vine Copula Handbook, pp. 233–247. World Scientific Publishing Co., Singapore.Search in Google Scholar

[43] Lemaire, M., A. Chateauneuf and J.-C. Mitteau (2010). Structural Reliability. Wiley, Hoboken NJ.Search in Google Scholar

[44] Malevergne, Y., D. Sornette (2003). Testing the Gaussian copula hypothesis for financial assets dependences. Quant. Finance 3(4), 231–250.10.1088/1469-7688/3/4/301Search in Google Scholar

[45] Massart P. (1990). The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. Ann. Probab. 18(3), 1269–1283.10.1214/aop/1176990746Search in Google Scholar

[46] McKay, M. D., R. J. Beckman and W. J. Conover (2000). A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 42(1), 55–61.10.1080/00401706.2000.10485979Search in Google Scholar

[47] McNeil, A. J. and J. Nešlehoá (2009). Multivariate Archimedean copulas, d-monotone functions and l-norm symmetric distributions. Ann. Statist. 37(5B), 3059–3097.10.1214/07-AOS556Search in Google Scholar

[48] Nápoles, O. M. (2010). Bayesian Belief Nets and Vines in Aviation Safety and other Applications. Ph.D. thesis, Delft University of Technology, Netherlands.Search in Google Scholar

[49] Nápoles O. M. Counting vines. In D. Kurowicka and H. Joe (Eds.), Dependence Modeling: Vine Copula Handbook, pp. 189–218. World Scientific Publishing Co., Singapore.Search in Google Scholar

[50] Nelsen, R. B. (2006). An Introduction to Copulas. Second edition. Springer, New York.Search in Google Scholar

[51] Newey, W. K. and D. McFadden (1994). Large sample estimation and hypothesis testing. Handb. Econom. 4, 2111–2245.Search in Google Scholar

[52] Osborne, M. A., R. Garnett, S. J. Roberts (2009). Gaussian processes for global optimization. 3rd International Conference on Learning and Intelligent Optimization (LION 3).Search in Google Scholar

[53] Pass B. (2015). Multi-marginal optimal transport: theory and applications. ESAIM Math. Model. Numer. Anal. 49(6), 1771–1790.10.1051/m2an/2015020Search in Google Scholar

[54] Robbins, H. and S. Monro (1951). A stochastic approximation method. Ann. Math. Stat. 22(3), 400–407.10.1214/aoms/1177729586Search in Google Scholar

[55] Rubino, G. and B. Tuffin (2009). Rare Event Simulation Using Monte Carlo Methods. Wiley, Chichester.10.1002/9780470745403Search in Google Scholar

[56] Saltelli, A., K. Chan and E. M. Scott (2000). Sensitivity Analysis. Wiley, New York.Search in Google Scholar

[57] Schoelzel, C. and P. Friederichs (2008). Multivariate non-normally distributed random variables in climate research - Introduction to the copula approach. Nonlin. Processes Geophys. 15(5), 761–772.10.5194/npg-15-761-2008Search in Google Scholar

[58] Sklar, M. (1959). Fonctions de répartition à n dimensions et leurs marges. Publ. Inst. Statist. Univ. Paris 8, 229–231.Search in Google Scholar

[59] Nilsen, T. and T. Aven (2003). Models and model uncertainty in the context of risk analysis. Reliab. Eng. Syst. Saf. 79(3), 309–317.10.1016/S0951-8320(02)00239-9Search in Google Scholar

[60] Tang, X. S., D. Q. Li, G. Rong, K. K. Phoon and C. B. Zhou (2013). Impact of copula selection on geotechnical reliability under incomplete probability information. Comput. Geotech. 49, 264–278.10.1016/j.compgeo.2012.12.002Search in Google Scholar

[61] Tang, X. S., D. Q. Li, C. B. Zhou and K. K. Phoon (2015). Copula-based approaches for evaluating slope reliability under incomplete probability information. Struct. Saf. 52, 90–99.10.1016/j.strusafe.2014.09.007Search in Google Scholar

[62] Thoft-Christensen, P. and J. D. Sørensen (1982). Reliability of structural systems with correlated elements. Appl. Math. Model. 6(3), 171–178.10.1016/0307-904X(82)90006-3Search in Google Scholar

[63] Torre, E., S. Marelli, P. Embrechts and B. Sudret (2019). Data-driven polynomial chaos expansion for machine learning regression. J. Comput. Phys. 388, 601–623.10.1016/j.jcp.2019.03.039Search in Google Scholar

[64] Torre, E., S. Marelli, P. Embrechts and B. Sudret (2019). A general framework for data-driven uncertainty quantification under complex input dependencies using vine copulas. Prob. Eng. Mech. 55, 1–16.10.1016/j.probengmech.2018.08.001Search in Google Scholar

[65] Van der Vaart, A. W. (2000). Asymptotic Statistics. Cambridge University Press.Search in Google Scholar

[66] Villani, C. (2008). Optimal Transport: Old and New. Springer, Berlin.Search in Google Scholar

[67] Zondervan-Zwijnenburg, M., W. van de Schoot-Hubeek, K. Lek, H. Hoijtink and R. van de Schoot (2017). Application and Evaluation of an Expert Judgment Elicitation Procedure for Correlations. Front. Psychol. 8, 1–15.10.3389/fpsyg.2017.00090Search in Google Scholar PubMed PubMed Central

Received: 2020-03-03
Accepted: 2020-08-31
Published Online: 2020-10-27

© 2020 Nazih Benoumechiara et al., published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Downloaded on 27.11.2022 from frontend.live.degruyter.dgbricks.com/document/doi/10.1515/demo-2020-0016/html
Scroll Up Arrow