Combined with advantages of moving least squares approximation, a new method for estimating higher-order conditional moment is established, which is useful for application in importance analysis and provides a supplement of the standard variance-based importance analysis. On the other hand, after obtaining the first four-order moments, the probability density function can be emulated by use of the Edgeworth expansion procedure, thereby a new method to compute the moment independent importance measure index proposed by Borgonovo is presented in this article. Two examples are employed to demonstrate that it is necessary to analyze higher-order conditional moment in importance analysis. At the same time, we study the feasibility of the Edgeworth expansion-based method for estimating the index by applying it to these examples.
SaltelliA. Sensitivity analysis for importance assessment. Risk Anal2002; 22(3): 579–590.
2.
SaltelliAChanKScottM. Sensitivity analysis. West Sussex, UK: Wiley, 2000, pp.1–51.
3.
BirnbaumZW. On the importance of different components in a multi-component system. In: Multi-variate analysis. New York: Academic Press, 1969, pp.581–592.
4.
SiSBDuiHYZhaoXB. Integrated importance measure of component states based on the loss of the performance. IEEE Trans Reliab2012; 61(1): 192–202.
5.
CheokMCParyGWSherryRR. Use of importance measure in risk-informed regulatory applications. Reliab Eng Syst Saf1998; 60(3): 213–226.
6.
BorgonovoEApostolakisGE. A new importance measure for risk-informed decision making. Reliab Eng Syst Saf2001; 72(2): 193–212.
7.
HeltonJCDavisFJ. Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems. Reliab Eng Syst Saf2003; 81: 23–69.
SaltelliAMarivoetJ. Non-parametric statistics in sensitivity analysis for model output: a comparison of selected techniques. Reliab Eng Syst Saf1990; 28: 229–253.
10.
SobolIM. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Mat Comput Simulation2001; 55(1): 221–280.
11.
ImanRLHanSC. A robust measure of uncertainty importance for use in fault tree system analysis. Risk Anal1990; 10(3): 401–406.
12.
RattoMPaganoAYoungPC. Non-parametric estimation of conditional moments for sensitivity analysis. Reliab Eng Syst Saf2009; 94: 237–243.
13.
HommaTSaltelliA. Use of Sobol’ quasirandom sequence generator for integration of modified uncertainty importance measure. J Nucl Sci Technol1995; 32(11): 1164–1173.
14.
ChunMHHanSJTakNI. An uncertainty importance measure using a distance metric for the change in a cumulative distribution function. Reliab Eng Syst Saf2000; 70(3): 313–321.
15.
BorgonovoE. A new uncertainty importance measure. Reliab Eng Syst Saf2007; 92(6): 771–784.
16.
LiuHBChenWSudjiantoA. Relative entropy based method for probabilistic sensitivity analysis in engineering design. J Mech Des2006; 128(3): 326–333.
17.
BorgonovoE. Measuring uncertainty importance: investigation and comparison of alternative approaches. Risk Anal2006; 26(5): 1349–1461.
BorgonovoECastaingsWTarantolaS. Emulators in moment independent sensitivity analysis: an application to environmental modelling. Environmental Modelling & Software2012; 34: 105–115.
20.
LiuQHommaT. A new computational method of a moment-independent uncertainty importance measure. Reliab Eng Syst Saf2009; 94(7): 1205–1211.
21.
LancasterPSalkauskasK. Surfaces generated by moving least squares methods. Math of Comput1981; 37(155): 141–158.
22.
DavidL. The approximation power of moving least-squares. Math of Comput1998; 67(224): 1517–1531.
23.
BreitkpfPNaceurHRassineuxA. Moving least squares response surface approximation: formulation and metal forming applications. Comp Struct2005; 83(17–18): 1411–1428.
24.
RosenbluethE. Point estimation for probability moments. Proc Nat Acad Sci1975; 72(10): 3812–3814.
25.
ZhaoYGOneT. New point estimates for probability moments. J Eng Mech2000; 126(4): 433–436.
26.
RuanWBLuZZTianLF. A modified variance-based importance measure and its solution by state dependent parameter. Proc IMechE, Part O: J Risk and Reliability2013; 227, 3–15.
27.
EffendyT. Derivation of moving least-squares approximation shape functions and its derivatives using the exponential weight function. Civil Engng Dimen2007; 9(1): 19–24.
28.
SilvermanBW. Density estimation for statistics and data analysis. London: Chapman & Hall, 1986.
29.
ScottDW. Multivariate density estimation: theory, practice and visualization. New York: Wiley, 1992.
30.
MaurizioFGuidoS. Approximate inference of the bandwidth in multivariate kernel density estimation. Compl Stats Data Analysis2001; 55: 3104–3122.
31.
ChengXLiWKYuLH. Modeling threshold conditional heteroscedasticity with regime-dependent skewness and kurtosis. Compl Stats Data Analysis2011; 55(9): 2590–2604.
32.
YeJSWangZGChenYL. Research on approximate methods of non-gaussian probability density function based on the first four moments of the response. J Logistical Engng Uni (in Chinese) 2010; 26(1): 12–16
33.
AssafSAZirkleLD. Approximate analysis of nonlinear stochastic system. Int J Control1976; 23(4): 477–492.
34.
JosseJPagèsJHussonF. Testing the significance of the RV coefficient. Compl Stats Data Analysis2008; 53: 82–91.
35.
IshigamiTHommaT. An importance quantification technique in uncertainty analysis for computer models. In: Proceedings of the ISUMA’90, First international symposium on uncertainty modeling and analysis, University of Maryland, 3–5 December 1990, pp.398–403.
