Talk:Sensitivity analysis
This is the talk page for discussing improvements to the Sensitivity analysis article. This is not a forum for general discussion of the article's subject. |
Article policies
|
Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL |
Archives: 1Auto-archiving period: 2 months |
The following Wikipedia contributor may be personally or professionally connected to the subject of this article. Relevant policies and guidelines may include conflict of interest, autobiography, and neutral point of view. |
This article is rated B-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects: | ||||||||||||||||||
|
Proposal for restoring some of the changes operated by User:MrOllie
[edit]This edit request by an editor with a conflict of interest was declined. A consensus could not be reached. |
Based on the above discussion in the present talk page, here is my attempt to re-establish essential references using the edit COI template. Andrea Saltelli Saltean (talk) 09:47, 19 January 2024 (UTC)
- Specific text to be added or removed: several sentences and references were added - ten references with me as co-author. The changes are motivated by the repeated interventions of User:MrOllie that have been deep and have left the page with errors. If and when the present editing are accepted, and even if they are not, the page will need housekeeping and cleaning. A solution will also need to be found for the sections that were eliminated and for which the community of sensitivity analysis practitioners[1] might be involved.
- Reason for the change: Relevance of the proposed insertion to the page, see discussion in the present talk page
- References supporting change: See in the present talk page the section entitle Top cited articles in sensitivity analysis with the number of citations
− | Sensitivity analysis is the study of how the uncertainty in the output of a mathematical model or system (numerical or otherwise) can be divided and allocated to different sources of uncertainty in its inputs. | + | Sensitivity analysis is the study of how the uncertainty in the output of a mathematical model or system (numerical or otherwise) can be divided and allocated to different sources of uncertainty in its inputs. |
− | The process of recalculating outcomes under alternative assumptions to determine the impact of a variable under sensitivity analysis can be useful for a range of purposes, including: | + | The process of recalculating outcomes under alternative assumptions to determine the impact of a variable under sensitivity analysis can be useful for a range of purposes, including: |
− | In models involving many input variables, sensitivity analysis is an essential ingredient of model building and quality assurance. National and international agencies involved in [[impact assessment]] studies have included sections devoted to sensitivity analysis in their guidelines. Examples are the [[European Commission]] (see e.g. the guidelines for [[impact assessment]]), the White House [[Office of Management and Budget]], the [[Intergovernmental Panel on Climate Change]] and [[US Environmental Protection Agency]]'s modeling guidelines | + | In models involving many input variables, sensitivity analysis is an essential ingredient of model building and quality assurance. National and international agencies involved in [[impact assessment]] studies have included sections devoted to sensitivity analysis in their guidelines. Examples are the [[European Commission]] (see e.g. the guidelines for [[impact assessment]]), the White House [[Office of Management and Budget]], the [[Intergovernmental Panel on Climate Change]] and [[US Environmental Protection Agency]]'s modeling guidelines. The practice of sensitivity analysis is described in several handbooks |
− | There are a large number of approaches to performing a sensitivity analysis, many of which have been developed to address one or more of the constraints discussed above. They are also distinguished by the type of sensitivity measure, be it based on (for example) variance decompositions, partial derivatives or elementary effects. In general, however, most procedures adhere to the following outline: | + | There are a large number of approaches to performing a sensitivity analysis, many of which have been developed to address one or more of the constraints discussed above. They are also distinguished by the type of sensitivity measure, be it based on (for example) variance decompositions, partial derivatives or elementary effects. In general, however, most procedures adhere to the following outline: |
− | Despite its simplicity however, this approach does not fully explore the input space, since it does not take into account the simultaneous variation of input variables. | + | Despite its simplicity however, this approach does not fully explore the input space, since it does not take into account the simultaneous variation of input variables. For this reason OAT is not advised when the degree of linearity of a model is unknown: an OAT analysis of a possibly nonlinear and non additive model can be ''perfunctory'', although many sensitivity analyses seen in the literature are OAT. The OAT approach |
− | A further measure, known as the ''total effect index'', gives the total variance in ''Y'' caused by ''X''<sub>''i''</sub> ''and'' its interactions with any of the other input variables. | + | A further measure, known as the ''total effect index'', gives the total variance in ''Y'' caused by ''X''<sub>''i''</sub> ''and'' its interactions with any of the other input variables. |
− | The Fourier amplitude sensitivity test (FAST) uses the [[Fourier series]] to represent a multivariate function (the model) in the frequency domain, using a single frequency variable. Therefore, the integrals required to calculate sensitivity indices become univariate, resulting in computational savings. | + | The Fourier amplitude sensitivity test (FAST) uses the [[Fourier series]] to represent a multivariate function (the model) in the frequency domain, using a single frequency variable. Therefore, the integrals required to calculate sensitivity indices become univariate, resulting in computational savings. FAST can be used to compute both the first order and the total effect sensitivity index. |
− | In order to take these concerns into due consideration the instruments of SA have been extended to provide an assessment of the entire knowledge and model generating process. This approach has been called 'sensitivity auditing'. | + | In order to take these concerns into due consideration the instruments of SA have been extended to provide an assessment of the entire knowledge and model generating process. This approach has been called 'sensitivity auditing'. |
− | Sensitivity analysis is closely related with uncertainty analysis; while the latter studies the overall [[uncertainty]] in the conclusions of the study, sensitivity analysis tries to identify what source of uncertainty weighs more on the study's conclusions. | + | Sensitivity analysis is closely related with uncertainty analysis; while the latter studies the overall [[uncertainty]] in the conclusions of the study, sensitivity analysis tries to identify what source of uncertainty weighs more on the study's conclusions. Sensitivity and analysis can be combined together when using approached such as [[Simulation decomposition|SimDec]]. |
− | Variance-based methods allow full exploration of the input space, accounting for interactions, and nonlinear responses. For these reasons they are widely used when it is feasible to calculate them. Typically this calculation involves the use of [[Monte Carlo integration|Monte Carlo]] methods, but since this can involve many thousands of model runs, other methods (such as emulators) can be used to reduce computational expense when necessary. | + | Variance-based methods allow full exploration of the input space, accounting for interactions, and nonlinear responses. For these reasons they are widely used when it is feasible to calculate them. Typically this calculation involves the use of [[Monte Carlo integration|Monte Carlo]] methods, but since this can involve many thousands of model runs, other methods (such as emulators) can be used to reduce computational expense when necessary. y. The full variance decompositions are only meaningful when the input factors are independent from one another. |
− | + | C |
Among the several section suppressed by User:MrOllie the following section (indicated in in red) includes the method of Morris that is one of the most widely used in sensitivity analysis. I propose to reinstate it as it was verbatim inserting it as a new section (as before) with a modified title: Morris Method.
Screening is a particular instance of a sampling-based method. The objective here is rather to identify which input variables are contributing significantly to the output uncertainty in high-dimensionality models, rather than exactly quantifying sensitivity (i.e. in terms of variance). Screening tends to have a relatively low computational cost when compared to other approaches, and can be used in a preliminary analysis to weed out uninfluential variables before applying a more informative analysis to the remaining set. One of the most commonly used screening method is the elementary effect method.[17][18]
In these proposed changes I have not suppressed text from other authors. Andrea Saltelli Saltean (talk) 09:57, 19 January 2024 (UTC)
References for the entire page Andrea Saltelli Saltean (talk) 15:13, 19 January 2024 (UTC)
- I can try evaluate them, though i only have deep knowledge in explainable AI. BikingFish (talk) 19:51, 27 January 2024 (UTC)
- Thanks User:BikingFish but this is a request done under 'Conflict of Interest' template, I understand this is for Wikipedia Editors, not for Authors like us. Here a interesting paper that might interest you in case you want to discuss it on Wikipedia, in this page or elsewhere.[19] Andrea Saltelli Saltean (talk) 11:18, 31 January 2024 (UTC)
- Comment - the section below is related to this request. STEMinfo (talk) 23:53, 27 March 2024 (UTC)
- I am marking this request as declined. Saltean, you have been told before that repeatedly asking for the removals to be reverted and appealing to your position as the leading academic on the subject will not convince people here. Either work on a rewrite as a draft as you were advised to at the administrators' noticeboard, or propose smaller changes that can be digested and evaluated. Snowmanonahoe (talk · contribs · typos) 19:16, 28 March 2024 (UTC)
References
- ^ SAMO Scientific Committee. 2022. “SAMO | Sensitivity Analysis of Model Output.” SAMO | Sensitivity Analysis of Model Output. 2022. https://www.sensitivityanalysis.org/.
- ^ Saltelli, Andrea. 2002. “Sensitivity Analysis for Importance Assessment.” In Risk Analysis, 22:579–90. https://doi.org/10.1111/0272-4332.00040.
- ^ a b Pannell, D. J. (1997). "Sensitivity Analysis of Normative Economic Models: Theoretical Framework and Practical Strategies" (PDF). Agricultural Economics. 16 (2): 139–152. doi:10.1016/S0169-5150(96)01217-0.
- ^ Saltelli, Andrea, S. Tarantola, and F. Campolongo. 2000. “Sensitivity Anaysis as an Ingredient of Modeling.” Statistical Science 15 (4): 377–95.
- ^ a b European Commission. 2021. “Better Regulation Toolbox.” November 25.
- ^ "Archived copy" (PDF). Archived from the original (PDF) on 2011-04-26. Retrieved 2009-10-16.
{{cite web}}
: CS1 maint: archived copy as title (link) - ^ "Archived copy" (PDF). Archived from the original (PDF) on 2011-04-26. Retrieved 2009-10-16.
{{cite web}}
: CS1 maint: archived copy as title (link) - ^ Saltelli, Andrea, Stefano Tarantola, Francesca Campolongo, and Marco Ratto. 2004. Sensitivity Analysis in Practice. Chichester, UK: John Wiley & Sons, Ltd. https://doi.org/10.1002/0470870958.
- ^ a b c Saltelli, Andrea, M. Ratto, T. H. Andres, F. Campolongo, J. Cariboni, D. Gatelli, M. Saisana, and S. Tarantola. 2008. Global Sensitivity Analysis : The Primer. John Wiley. https://doi.org/10.1002/9780470725184.
- ^ Da Veiga, Sébastien, Fabrice Gamboa, Bertrand Iooss, and Clémentine Prieur. 2021. Basics and Trends in Sensitivity Analysis. SIAM. https://blackwells.co.uk/bookshop/product/Basics-and-Trends-in-Sensitivity-Analysis-by-Sbastien-da-Veiga-Fabrice-Gamboa-Bertrand-Iooss-Clmentine-Prieur/9781611976687.
- ^ Saltelli, Andrea, and Paola Annoni. 2010. ‘How to Avoid a Perfunctory Sensitivity Analysis’. Environmental Modelling & Software 25 (12): 1508–17. https://doi.org/10.1016/j.envsoft.2010.04.012.
- ^ Ferretti, Federico, Andrea Saltelli, and Stefano Tarantola. 2016. ‘Trends in Sensitivity Analysis Practice in the Last Decade’. Science of The Total Environment 568 (October): 666–70. https://doi.org/10.1016/j.scitotenv.2016.02.133.
- ^ Homma, Toshimitsu, and Andrea Saltelli. 1996. ‘Importance Measures in Global Sensitivity Analysis of Nonlinear Models’. Reliability Engineering & System Safety 52 (1): 1–17. https://doi.org/10.1016/0951-8320(96)00002-6.
- ^ Saltelli, Andrea, S. Tarantola, and K. P.-S. Chan. 1999. “A Quantitative Model-Independent Method for Global Sensitivity Analysis of Model Output.” Technometrics 41 (1): 39–56. https://doi.org/10.1080/00401706.1999.10485594.
- ^ Saltelli, Andrea, Ângela; Guimaraes Pereira, Jeroen P. van der Sluijs, and Silvio Funtowicz. 2013. “What Do I Make of Your Latinorumc Sensitivity Auditing of Mathematical Modelling.” International Journal of Foresight and Innovation Policy 9 (2/3/4): 213–34. https://doi.org/10.1504/IJFIP.2013.058610.
- ^ Saltelli, A.; Tarantola, S. (2002). "On the relative importance of input factors in mathematical models: safety assessment for nuclear waste disposal". Journal of the American Statistical Association. 97 (459): 702–709. doi:10.1198/016214502388618447. S2CID 59463173.
- ^ Morris, M. D. (1991). "Factorial sampling plans for preliminary computational experiments". Technometrics. 33 (2): 161–174. CiteSeerX 10.1.1.584.521. doi:10.2307/1269043. JSTOR 1269043.
- ^ Campolongo, F.; Cariboni, J.; Saltelli, A. (2007). "An effective screening design for sensitivity analysis of large models". Environmental Modelling and Software. 22 (10): 1509–1518. doi:10.1016/j.envsoft.2006.10.004. S2CID 15357037.
- ^ Iooss, B., Kenett, R. S., Secchi, P. (16 October 2022). "Interpretability for Industry 4.0 : Statistical and Machine Learning Approaches". Different views of interpretability (Antonio Lepore, Boagio Palumbo, Jean-Michel Poggi ed.). Springer International Publishing. ISBN 978-3-031-12401-3.