Sample-based estimation of correlation ratio with polynomial approximation

@article{Lewandowski2007SamplebasedEO,
  title={Sample-based estimation of correlation ratio with polynomial approximation},
  author={Daniel Lewandowski and Roger M. Cooke and Radboud J. Duintjer Tebbens},
  journal={ACM Trans. Model. Comput. Simul.},
  year={2007},
  volume={18},
  pages={3:1-3:17}
}
Sensitivity analysis has become a natural step in the uncertainty analysis framework. As there is no general sensitivity measure that would capture all information on impact of input factors on model output, analysts tend to combine various measures to obtain a broader image of interactions between different modes. This article concentrates on the correlation ratio, demonstrates methods for calculating this quantity efficiently and accurately, and compares the results. A new method inspired by… Expand
Moment independent importance measures: new results and analytical test cases.
TLDR
A methodology that allows one to obtain moment independent sensitivity measures analytically is introduced and illustrated by implementing four test cases with different model structures and model input distributions. Expand
Uncertainty importance measure for models with correlated normal variables
TLDR
The contribution decomposition of the correlated input variables based on Mara's definition is investigated in detail and the derived analytical solutions can directly be used to recognize the contributions by the correlatedinput variables in case of the quadratic or linear polynomial output without cross term. Expand
Variance-based sensitivity indices for models with dependent inputs
TLDR
A set of variance-based sensitivity indices are proposed to perform sensitivity analysis of models with dependent inputs and allow us to distinguish between the mutual dependent contribution and the independent contribution of an input to the model response variance. Expand
An adaptive correlation ratio method using the cumulative sum of the reordered output
  • E. Plischke
  • Mathematics, Computer Science
  • Reliab. Eng. Syst. Saf.
  • 2012
TLDR
This work considers correlation ratios as estimators for first order sensitivity indices from given data and simplifies the computation by the introduction of the cumulative sum of the normalised reordered output. Expand
Probability models for data-Driven global sensitivity analysis
TLDR
A probability model-based global sensitivity analysis (PM-GSA) framework, to compute various Sobol’ indices when only input-output data are available, is presented and four numerical examples are used to demonstrate the effectiveness of the proposed method. Expand
Global Sensitivity Analysis with Small Sample Sizes: Ordinary Least Squares Approach.
TLDR
A new version of global sensitivity analysis coupled with tools from statistics, machine learning, and optimization can devise small sample sizes that allow for the accurate ordering of sensitivity coefficients for the first 10-30 most sensitive chemical reactions in complex chemical-kinetic mechanisms, and is particularly useful for studying the chemistry in realistic devices. Expand
Polynomial chaos expansion for sensitivity analysis
TLDR
It is shown that when the model output is smooth with regards to the inputs, a spectral convergence of the computed sensitivity indices is achieved, but even for smooth outputs the method is limited to a moderate number of inputs, as it becomes computationally too demanding to reach the convergence domain. Expand
Sensitivity analysis: A review of recent advances
TLDR
This work investigates in detail the methodological issues concerning the crucial step of correctly interpreting the results of a sensitivity analysis, and presents recent results that permit the estimation of global sensitivity measures by post-processing the sample generated by a traditional Monte Carlo simulation. Expand
Addressing factors fixing setting from given data: A comparison of different methods
TLDR
The results show that the polynomial chaos expansion for estimating Sobol indices via sparse PCE are found to be the most efficient approach. Expand
An effective strategy for combining variance- and distribution-based global sensitivity analysis
TLDR
A new strategy for performing global sensitivity analysis capable to estimate main and interaction effects from a generic sampling design based on a meaningful combination of variance- and distribution-based approaches is presented. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 39 REFERENCES
Sample-based estimation of correlation ratio with polynomial approximation
TLDR
This research presents a novel and scalable approach called "Smart Cassandra Integration (SCSI)” that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of estimating the sensitivity of inputs to an uncertainty analysis framework. Expand
Nonparametric variance-based methods of assessing uncertainty importance
Abstract This paper examines the feasibility and value of using nonparametric variance-based methods to supplement parametric regression methods for uncertainty analysis of computer models. It showsExpand
Sensitivity analysis of model output: variance-based methods make the difference
TLDR
The methods that will be discussed and used to perform SA in this paper are called ‘Variancebased methods’, in that the variability, or uncertainty, associated with an important input parameter is propagated through the model resulting in a large contribution to the overall output variability. Expand
Sensitivity Analysis as an Ingredient of Modeling
We explore the tasks where sensitivity analysis (SA) can be useful and try to assess the relevance of SA within the modeling process. We suggest that SA could considerably assist in the use ofExpand
A quantitative model-independent method for global sensitivity analysis of model output
A new method for sensitivity analysis (SA) of model output is introduced. It is based on the Fourier amplitude sensitivity test (FAST) and allows the computation of the total contribution of eachExpand
An importance quantification technique in uncertainty analysis for computer models
  • T. Ishigami, T. Homma
  • Computer Science
  • [1990] Proceedings. First International Symposium on Uncertainty Modeling and Analysis
  • 1990
TLDR
The authors have developed a technique to numerically quantify importance of input variables including uncertainties to the output uncertainty, based on the concept of uncertainty reduction, which makes it practically possible to estimate the importance measure proposed by Hora and Iman (1986). Expand
Sensitivity Analysis
Recall that in order to formulate a problem as a linear program, you had to invoke a certainty assumption: you had to know what value the data took on, and you have made decisions based on that data.Expand
Probabilistic sensitivity analysis of complex models: a Bayesian approach
In many areas of science and technology, mathematical models are built to simulate complex real world phenomena. Such models are typically implemented in large computer programs and are also veryExpand
Uncertainty and Sensitivity Analyses of a Dynamic Economic Evaluation Model for Vaccination Programs
TLDR
The authors find that the magnitudes and rankings of sensitivity measures depend on the selected method(s) and make recommendations regarding the choice of method depending on the complexity of the model, number of uncertain inputs, and desired types of insights from the sensitivity analysis. Expand
A Quantitative Model-Independent Method for Global Sensitivity Analysis of Model Output
TLDR
Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content. Expand
...
1
2
3
4
...