Variance decomposition and global sensitivity for structural systems

2010 ◽  
Vol 32 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Sanjay R. Arwade ◽  
Mohammadreza Moradi ◽  
Arghavan Louhghalam
Keyword(s):  
Variance Decomposition ◽  
Structural Systems ◽  
Global Sensitivity

Regional importance measures based on failure probability in the presence of epistemic and aleatory uncertainties

2013 ◽  
Vol 228 (6) ◽  
pp. 1029-1047 ◽  
Author(s):  
Lei Cheng ◽  
Zhenzhou Lu ◽  
Luyi Li
Keyword(s):  
Failure Probability ◽  
Computational Cost ◽  
Variance Decomposition ◽  
The State ◽  
Structural Systems ◽  
Conditional Mean ◽  
First Order ◽  
State Dependent ◽  
Main Effect ◽  
Dependent Parameter

For the structural systems with both epistemic and aleatory uncertainties, in order to analyze the effects of different regions of epistemic parameters on failure probability, two regional importance measures (RIMs) are firstly proposed, i.e. contribution to mean of failure probability (CMFP) and contribution to variance of failure probability (CVFP), and their properties are analyzed and verified. Then, to analyze the effect of different regions of the epistemic parameters on their corresponding first-order variance (i.e. main effect) in the Sobol’s variance decomposition, another RIM is proposed which is named as contribution to variance of conditional mean of failure probability (CVCFP). The proposed CVCFP is then extended to define another RIM named as contribution to mean of conditional mean of failure probability, i.e. CMCFP, to measure the contribution of regions of epistemic parameters to mean of conditional mean of failure probability. For the problem that the computational cost for calculating the conditional mean of failure probability may be too large to be accepted, the state dependent parameter (SDP) method is introduced to estimate CVCFP and CMCFP. Several examples are used to demonstrate the effectiveness of the proposed RIMs and the efficiency and accuracy of the SDP-based method are also demonstrated by the examples.

Analytical global sensitivity analysis with Gaussian processes

2017 ◽  
Vol 31 (3) ◽  
pp. 235-250 ◽  
Author(s):  
Ankur Srivastava ◽  
Arun K. Subramaniyan ◽  
Liping Wang
Keyword(s):  
Sensitivity Analysis ◽  
Gaussian Processes ◽  
Global Sensitivity Analysis ◽  
Decomposition Methods ◽  
Variance Decomposition ◽  
Model Representation ◽  
High Dimensional ◽  
High Dimensional Model Representation ◽  
Sobol Indices ◽  
Global Sensitivity

AbstractMethods for efficient variance-based global sensitivity analysis of complex high-dimensional problems are presented and compared. Variance decomposition methods rank inputs according to Sobol indices that can be computationally expensive to evaluate. Main and interaction effect Sobol indices can be computed analytically in the Kennedy and O'Hagan framework with Gaussian processes. These methods use the high-dimensional model representation concept for variance decomposition that presents a unique model representation when inputs are uncorrelated. However, when the inputs are correlated, multiple model representations may be possible leading to ambiguous sensitivity ranking with Sobol indices. In this work, we present the effect of input correlation on sensitivity analysis and discuss the methods presented by Li and Rabitz in the context of Kennedy and O'Hagan's framework with Gaussian processes. Results are demonstrated on simulated and real problems for correlated and uncorrelated inputs and demonstrate the utility of variance decomposition methods for sensitivity analysis.

scholarly journals On the consistency of Sobol indices with respect to stochastic ordering of model parameters

2019 ◽  
Vol 23 ◽  
pp. 387-408 ◽  
Author(s):  
A. Cousin ◽  
A. Janon ◽  
V. Maume-Deschamps ◽  
I. Niang
Keyword(s):  
Sensitivity Analysis ◽  
Uncertainty Quantification ◽  
Global Sensitivity Analysis ◽  
Stochastic Ordering ◽  
Variance Decomposition ◽  
Stochastic Orders ◽  
Model Parameters ◽  
Sobol Indices ◽  
Global Sensitivity ◽  
The Past

In the past decade, Sobol’s variance decomposition has been used as a tool to assess how the output of a model is affected by the uncertainty on its input parameters. We show some links between global sensitivity analysis and stochastic ordering theory. More specifically, we study the influence of inputs’ distributions on Sobol indices in relation with stochastic orders. This gives an argument in favor of using Sobol’s indices in uncertainty quantification, as one indicator among others.

Variance Based Global Sensitivity Analysis for Uncorrelated and Correlated Inputs With Gaussian Processes

2015 ◽  
Author(s):  
Ankur Srivastava ◽  
Arun K. Subramaniyan ◽  
Liping Wang
Keyword(s):  
Sensitivity Analysis ◽  
Gaussian Processes ◽  
Global Sensitivity Analysis ◽  
Decomposition Methods ◽  
Variance Decomposition ◽  
Model Representation ◽  
High Dimensional ◽  
High Dimensional Model Representation ◽  
Sobol Indices ◽  
Global Sensitivity

Methods for efficient variance based global sensitivity analysis of complex high-dimensional problems are presented and compared. Variance decomposition methods rank inputs according to Sobol indices which can be computationally expensive to evaluate. Main and interaction effect Sobol indices can be computed efficiently in the Kennedy & O’Hagan framework with Gaussian Processes (GPs). These methods use the High Dimensional Model Representation (HDMR) concept for variance decomposition which presents a unique model representation when inputs are uncorrelated. However, when the inputs are correlated, multiple model representations may be possible leading to ambiguous sensitivity ranking with Sobol indices. In this work we present the effect of input correlation on sensitivity analysis and discuss the methods presented by Li & Rabitz in the context of Kennedy & O’ Hagan framework with GPs. Results are demonstrated on simulated and real problems for correlated and uncorrelated inputs and demonstrate the utility of variance decomposition methods for sensitivity analysis.

POST-TENSIONED STRUCTURAL SYSTEMS - DALLAS-FT. WORTH AIRPORT

PCI Journal ◽  
1973 ◽  
Vol 18 (6) ◽  
pp. 72-91
Author(s):  
Eugene A. Lamberson
Keyword(s):  
Structural Systems ◽  
Post Tensioned

Non-Performing Loans, Banking System and Macroeconomy

2018 ◽  
Vol 63 (2) ◽  
pp. 67-86
Author(s):  
Akinola Morakinyo ◽  
Colette Muller ◽  
Mabutho Sibanda
Keyword(s):  
Exchange Rate ◽  
Serial Correlation ◽  
Banking System ◽  
Impulse Response Function ◽  
Credit Market ◽  
Variance Decomposition ◽  
Structural Var ◽  
Long Run ◽  
Correlation Tests ◽  
The Exchange Rate

Abstract The study builds on previous studies of the consequences of non-performing loans on an economy. Using a seven-by-seven matrix in the impulse response function (IRF) of the structural autoregressive model, we find a long-run impact of an impulse to non-performing loans on the banking system and the macroeconomy in Nigeria. Conversely, non-performing loans also respond to the innovation of all macro-banking variables aside from the exchange rate and the growth rate to GDP. Also, the level of non-performing loans grows in influence in relation to the changes to the exchange rate using the variance decomposition tool of Structural VAR. Hence, a prominent role is assigned to the level of NPLs in linking the friction in the credit market to the susceptibility of both the banking system and the macroeconomy. This study passes the serial correlation tests and the three tests of normality.

Sign in / Sign up

Export Citation Format

Share Document