The PAWN index is gaining traction among the modelling community as a sensitivity measure. However, the robustness to its design parameters has not yet been scrutinized: the size ($N$) and sampling ($\epsilon$) of the model output, the number of conditioning intervals ($n$) or the summary statistic ($\theta$). Here we fill this gap by running a sensitivity analysis of a PAWN-based sensitivity analysis. We compare the results with the design uncertainties of the Sobol’ total-order index ($S_{Ti}^{\ast }$). Unlike in $S_{Ti}^{\ast }$, the design uncertainties in PAWN create non-negligible chances of producing biased results when ranking or screening inputs. The dependence of PAWN upon ($N,n,\epsilon ,\theta$) is difficult to tame, as these parameters interact with one another. Even in an ideal setting in which the optimum choice for ($N,n,\epsilon ,\theta$) is known in advance, PAWN might not allow to distinguish an influential, non-additive model input from a truly non-influential model input.

作为敏感性度量，PAWN指数在建模社区中越来越受欢迎。但是，尚未对其设计参数的稳健性进行审查：尺寸（$ñ$）和采样（$\epsilon$）的模型输出，调理间隔数（$ñ$）或摘要统计信息（$\theta$）。在这里，我们通过对基于PAWN的敏感性分析进行敏感性分析来填补这一空白。我们将结果与Sobol总订单指数的设计不确定性进行比较（${\mathrm{小号}}_{Ť\mathrm{一世}}^{\ast }$）。不像在${\mathrm{小号}}_{Ť\mathrm{一世}}^{\ast }$，PAWN中的设计不确定性会在对输入进行排名或筛选时，产生产生偏差结果的机会微不足道。PAWN对（$ñ，ñ，\epsilon ，\theta$）很难驯服，因为这些参数会相互影响。即使在理想的环境中，（$ñ，ñ，\epsilon ，\theta$）是事先已知的，PAWN可能不允许将有影响的，非加性的模型输入与真正的无影响的模型输入区分开。