New statistical methodology for second-level global sensitivity analysis of numerical simulators

International audienceGlobal sensitivity analysis (GSA) of numerical simulators aims at studying the global impact of the input uncertainties on the output. To perform the GSA, statistical tools based on inputsoutput dependence measures are commonly used. We focus here on dependence measures based on reproducing kernel Hilbert spaces the Hilbert-Schmidt Independence Criterion denoted HSIC. Sometimes, the probability distributions modeling the uncertainty of inputs may be themselves uncertain and it is important to quantify the global impact of this uncertainty on GSA results. We call it here the second-level global sensitivity analysis (GSA2). However, GSA2, when performed with a double Monte Carlo loop, requires a large number of model evaluations which is intractable with CPU time expensive simulators. To cope with this limitation, we propose a new statistical methodology based on a single Monte Carlo loop with a limited calculation budget. Firstly, we build a unique sample of inputs from a well chosen probability distribution and the associated code outputs are computed. From this inputsoutput sample, we perform GSA for various assumed probability distributions of inputs by using weighted HSIC measures estimators. Statistical properties of these weighted estimators are demonstrated. Finally, we define 2nd-level HSIC-based measures between the probability distributions of inputs and GSA results, which constitute GSA2 indices. The efficiency of our GSA2 methodology is illustrated on an analytical example, thereby comparing several technical options. Finally, an application to a test case simulating a severe accidental scenario on nuclear reactor is provided