Floodgate: inference for model-free variable importance
Floodgate: inference for model-free variable importance
复制标题
Floodgate：无模型变量重要性的推断
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Lucas Janson
中科院分区：
文献类型：
--
作者：
Lu Zhang;Lucas Janson
许多现代应用程序试图理解结果变量Y和协变量X在存在（可能是高维的）混杂变量Z的情况下的关系。虽然很多注意力已经支付给测试是否$Y$取决于$X$给定$Z$，在本文中，我们试图超越测试推断的强度，依赖。我们首先定义我们的被估量，最小均方误差（mMSE）差距，它量化的方式，是确定性的，无模型的，可解释的，和敏感的非线性和相互作用的条件之间的关系$Y$和$X$。然后，我们提出了一种新的推理方法，称为闸门，可以利用用户选择的任何工作回归函数（允许，例如，它将由最先进的机器学习算法拟合或从定性领域知识导出）来构建渐近置信界限，并将其应用于mMSE差距。除了证明闸门的渐近有效性，我们严格量化其准确性（距离置信区间估计）和鲁棒性。我们展示了洪水闸门的性能在一系列的模拟，并将其应用于英国生物银行的数据，以推断血小板计数对各组基因突变的依赖性的强度。
Many modern applications seek to understand the relationship between an outcome variable $Y$ and a covariate $X$ in the presence of a (possibly high-dimensional) confounding variable $Z$. Although much attention has been paid to testing whether $Y$ depends on $X$ given $Z$, in this paper we seek to go beyond testing by inferring the strength of that dependence. We first define our estimand, the minimum mean squared error (mMSE) gap, which quantifies the conditional relationship between $Y$ and $X$ in a way that is deterministic, model-free, interpretable, and sensitive to nonlinearities and interactions. We then propose a new inferential approach called floodgate that can leverage any working regression function chosen by the user (allowing, e.g., it to be fitted by a state-of-the-art machine learning algorithm or be derived from qualitative domain knowledge) to construct asymptotic confidence bounds, and we apply it to the mMSE gap. In addition to proving floodgate's asymptotic validity, we rigorously quantify its accuracy (distance from confidence bound to estimand) and robustness. We demonstrate floodgate's performance in a series of simulations and apply it to data from the UK Biobank to infer the strengths of dependence of platelet count on various groups of genetic mutations.
登录
查看更多内容
影响因子：
16.6
作者：
Matteo Sesia;E. Katsevich;Stephen Bates;E. Candès;C. Sabatti
通讯作者：
Matteo Sesia;E. Katsevich;Stephen Bates;E. Candès;C. Sabatti
影响因子：
5.7
作者：
Buja, Andreas;Brown, Lawrence;Zhao, Linda
通讯作者：
Zhao, Linda
影响因子：
0.8
作者：
Li,Lingling;Tchetgen,EricTchetgen;vanderVaart,Aad;Robins,JamesM
通讯作者：
Robins,JamesM
影响因子：
1.1
作者：
Robins J;Tchetgen Tchetgen E;Li L;van der Vaart A
通讯作者：
van der Vaart A
DOI：
10.1073/pnas.2007743117
发表时间：
2020-09-29
影响因子：
11.1
作者：
Bates S;Sesia M;Sabatti C;Candès E
通讯作者：
Candès E