Sensitivity Analysis

Sensitivity Settings

Sensitivity Methods

There are 5 sensitivity analysis methods incorporated into the tool. These can be selected from the 'Sensitivity' section.

For more information about how each method works, read the linked publication papers:

Sobol

Saltelli, A., Annoni, P., Azzini, I., Campolongo, F., Ratto, M., & Tarantola, S. (2010). Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index. Computer Physics Communications, 181(2), 259–270. https://doi.org/10.1016/j.cpc.2009.09.018

Sobol′, I. M. (2001). Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Mathematics and Computers in Simulation, 55(1–3), 271–280. https://doi.org/10.1016/S0378-4754(00)00270-6

Fourier Amplitude Sensitivity Test (FAST)

Saltelli, A., & Bolado, R. (1998). An alternative way to compute Fourier amplitude sensitivity test (FAST). Computational Statistics & Data Analysis, 26(4), 445–460. https://doi.org/10.1016/S0167-9473(97)00043-1

Random Balance Designs – FAST

Tarantola, S., Gatelli, D., & Mara, T. A. (2006). Random balance designs for the estimation of first order global sensitivity indices. Reliability Engineering & System Safety, 91(6), 717–727. https://doi.org/10.1016/j.ress.2005.06.003

Tissot, J.-Y., & Prieur, C. (2012). Bias correction for the estimation of sensitivity indices based on random balance designs. Reliability Engineering & System Safety, 107, 205–213. https://doi.org/10.1016/j.ress.2012.06.010

Delta-Moment Independent Measure

Borgonovo, E. (2007). A new uncertainty importance measure. Reliability Engineering & System Safety, 92(6), 771–784. https://doi.org/10.1016/j.ress.2006.04.015

Plischke, E., Borgonovo, E., & Smith, C. L. (2013). Global sensitivity measures from given data. European Journal of Operational Research, 226(3), 536–550. https://doi.org/10.1016/j.ejor.2012.11.047

Other Settings

You can select you can select seed in order to set the sample size. The sample size depends on the number of parameters. For LH-OFAT, use at least 500 samples for reliable results and use about a thousand and above for other methods. Parallel processes help reduce runtimes of sensitivity analysis and can reduce to between less than half the expected time.

You can also set the objective function to use for sensitivity analysis.

If you do not have observations for what you want to run, you can set the, use observations to 'No' and select what you want to run sensitivity for. Remember to activate output for the variable and the desired timestep in print settings under 'Run Model' section.

You are now ready to run sensitivity analysis.

Running Sensitivity

While Sensitivity Analysis is running, you will be able to see the progress through process progress bars and total percent complete. if you select a parameter, you can also see a live update of dotty plots fror the sensitivity analysis for that specific parameter.

Analysing Sensitivity Results

When sensitivity analysis is complete, you can see the first order sensitivity indices. clicking on the column header sorts accending or descending. You may see some small negative numbers, especially when using Sobol Method. This happens due to numerical issues, you can take these as non-sensitive.