原标题：Variance-based sensitivity indices formodels with dependent inputs
作者：Thierry A. Mara, Stefano Tarantola
关键词：ANOVA-HDMR; Dependent inputs;Variance-based sensitivity indices; Dependent contributions; Independentcontributions
中文摘要：计算模型在工程中广泛用于风险分析或预测未来的结果。不确定性和灵敏度分析在这些方面有很大的帮助。虽然有几种方法可以对具有独立输入的模型输出进行基于方差的灵敏度分析，但在相关输入的情况下，文献中只提出了几种方法。这可以通过以下事实来解释:建立了独立情况的理论框架，并定义了一组基于方差的灵敏度指数。在目前的工作中，我们提出了一套基于方差的灵敏度指数，以执行灵敏度分析的模型与相关的输入。这些措施使我们能够区分相互依赖的贡献和一个输入对模型响应方差的独立贡献。它们的定义依赖于输入的特定正交化和模型输出的基于方差分析的表示。在实际应用中，提出了简化模型的灵敏度指标。
英文摘要：Computational models are intensivelyused in engineering for risk analysis or prediction of future outcomes.Uncertainty and sensitivity analyses are of great help in these purposes.Although several methods exist to perform variance-based sensitivity analysisof model output with independent inputs only a few are proposed in theliterature in the case of dependent inputs. This is explained by the fact thatthe theoretical framework for the independent case is set and a univocal set ofvariance-based sensitivity indices is defined. In the present work, we proposea set of variance-based sensitivity indices to perform sensitivity analysis ofmodels with dependent inputs. These measures allow us to distinguish betweenthe mutual dependent contribution and the independent contribution of an inputto the model response variance. Their definition relies on a specificorthogonalisation of the inputs and ANOVA-representations of the model output.In the applications, we show the interest of the new sensitivity indices formodel simplification setting.
文献总结：
