Confareneoclassico / Variance_SA_estimators_designs_explorativity_economy

Reliability Engineering and System Safety

A new sample-based algorithm to compute the total sensitivity index

This repository contains the Python code implemented to i) compare the Glen&Isaacs estimator (2012) against the Saltenis estimator (Saltelli 2010); ii) the Saltenis estimator and the Lamboni estimator (2018); iii) the algorithm to improve the performance of the Saltenis estimator that tunes the number of runs to the value of the index assessed.

The Matlab(R) scripts have been developed by Federico Ferretti, JRC [e-mail]

References

Glen G., Isaacs, K., 2012, Estimating Sobol’ sensitivity indices using correlations, Environmental Modelling and Software 37, 157-166.

Lamboni, M. (2018). Global sensitivity analysis: a generalized, unbiased and optimal estimator of total-effect variance. Statistical Papers, 59(1)

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.