Comment on "A Monte Carlo filtering application for systematic sensitivity analysis of computable general equilibrium results"

In a recent article published in the Journal of Economic Systems Research, Mary et al. (2018) introduced an interesting approach to systematic sensitivity analysis applied in a Computable General Equilibrium (CGE) modelling framework. This approach offers a systematic method of identifying the model parameters that have the greatest impact on the uncertainty of model output. According to the authors, moreover, it increases the quality of the approximated results by decreasing the dimensionality of the problem. This article contributes to a recent set of studies discussing the accuracy and appropriateness of different uncertainty analysis methods in economic simulation models. While the focus of the article is on a more efficient way of sensitivity analysis, we see a problem in using an arbitrary rotation of Stroud's octahedron as a benchmark for assessing Monte Carlo simulations.