Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index

By Andrea Saltelli, Paola Annoni, Ivano Azzini, Francesca Campolongo, Marco Ratto, Stefano Tarantola. Computer Physics Communications, 2010

3,200 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Mechanics of Materials, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/68979cee1e73dae012ece8ddc4037356d1b5e135

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Francesca Pianosi
2. Thorsten Wagener
3. Emanuele Borgonovo
4. Zeliang Liu
5. Hoshin V. Gupta
6. Wing Kam Liu
7. Fabrice Gamboa
8. L. G. G. de Gonçalves

In Mechanics of Materials

1. Bertrand Iooss
2. Thorsten Wagener
3. Francesca Pianosi
4. Jon Herman
5. Will Usher
6. Michaela Saisana
7. Sergei S. Kucherenko
8. Zeliang Liu

In Statistics and Probability

1. Thorsten Wagener
2. Francesca Pianosi
3. Bertrand Iooss
4. Jon Herman
5. Will Usher
6. Fabrice Gamboa
7. Emanuele Borgonovo
8. Michaela Saisana

Citations in the corpus

• Variance-based global sensitivity analysis for multiple scenarios and models with implementation using sparse grid collocation (2015, methodology): “All the results in Sections 4.1– 4.5 are based on the quasi-random sampling method of Saltelli et al. (2010).”
• Sobol' sensitivity analysis of a complex environmental model (2011, methodology): “Obviously, the estimation of the integral becomes more accurate for higher values of n. Saltelli et al. (2010) suggest to use two independent input sample n  p -matrices (the " sample " matrix M 1 and the " resample " matrix M 2 ) to compute the Monte Carlo integrals, where n is the sample size…”
• Computational microstructure characterization and reconstruction: Review of the state-of-the-art techniques (2018, methodology): “…the randomness), estimate their properties (e.g., via the finite element method, FEM), and then proceed to build PSP links and conduct statistical analyses (such as sensitivity analysis [50], model calibration and bias correction [45], and uncertainty quantification and propagation [33,43,46,51,52]).”
• Efficient posterior exploration of a high‐dimensional groundwater model from two‐stage Markov chain Monte Carlo simulation and polynomial chaos expansion (2013, methodology): “To avoid underestimating the sensitivity of ~F P to the KL modes, we performed a second standard Sobol’ sensitivity analysis of ~F P but this time using Jansen formulations [see, e.g., Saltelli et al., 2010], with each KL mode varying between 3 and 3.”
• A simple and efficient method for global sensitivity analysis based on cumulative distribution functions (2015, positive): “Specifically, when using the efficient estimators reviewed in Saltelli et al. (2010), the total number of model evaluations grows linearly with the number of uncertain inputs according to the formula N ¼ n (M þ 2) where N is the number of model evaluations, M is the number of inputs M and n is the…”
• Ratings and rankings: voodoo or science? (2011, background): “Si can be estimated from design points: Sobol’ (1993); Saltelli (2002); Saltelli et al. (2010); Fourier analysis: Tarantola et al. (2006); Plischke (2010); Xu and Gertner (2011), or others.”