Applications of Dynamic Trees to Sensitivity Analysis

A recent approach to surrogate modelling, called dynamic trees, uses regression trees to partition the input space, and fits simple constant or linear models in each “leaf” (region of the input space). This article aims to investigate the applicability of dynamic trees in sensitivity analysis, in particular on high dimensional problems at low sample size, to see whether they can be applied to dimensionalities usually out of the range of surrogate models. Comparisons are made with Gaussian processes, as well as three measures based on a radial sampling scheme: the Monte Carlo estimator of the total sensitivity index, an elementary effects measure, and a derivative-based sensitivity measure. The results show that the radial sampling measures generally outperform the surrogate models tested here, with the exception of response surfaces that feature discontinuities.JRC.DDG.01-Econometrics and applied statistic