Local Linear Forests

Local Linear Forests
复制标题

局部线性森林

DOI:
10.1080/10618600.2020.1831930
复制
发表时间:
2021
影响因子:
2.4
通讯作者:
Wager, Stefan
Wager, Stefan
中科院分区:
数学2区
文献类型:
--
作者:
Friedberg, Rina;Tibshirani, Julie;Athey, Susan;Wager, Stefan

文献摘要

参考文献

被引文献

相似文献

随机森林是非参数回归的一种强大方法,但其拟合平滑信号的能力有限。从随机森林的角度来看,作为一种自适应核方法,我们将森林核与局部线性回归调整配对,以更好地捕获平滑性。由此产生的程序,当地的线性森林,使我们能够提高渐近收敛速度的随机森林与平滑信号,并提供了大量的收益,在准确性上的真实的和模拟数据。我们证明了一个中心极限定理有效的森林和光滑约束的正则性条件下,并提出了一个计算效率的置信区间的建设。移动到因果推理的应用程序,我们讨论了异质性治疗效果估计的本地回归调整的优点,并给出了一个例子的数据集上探索字的选择对社会安全网的态度的影响。最后,我们包括模拟结果的真实的和生成的数据。软件实现在R包grf中可用。本文的补充材料可在网上查阅。
Random forests are a powerful method for nonparametric regression, but are limited in their ability to fit smooth signals. Taking the perspective of random forests as an adaptive kernel method, we pair the forest kernel with a local linear regression adjustment to better capture smoothness. The resulting procedure,local linear forests, enables us to improve on asymptotic rates of convergence for random forests with smooth signals, and provides substantial gains in accuracy on both real and simulated data. We prove a central limit theorem valid under regularity conditions on the forest and smoothness constraints, and propose a computationally efficient construction for confidence intervals. Moving to a causal inference application, we discuss the merits of local regression adjustments for heterogeneous treatment effect estimation, and give an example on a dataset exploring the effect word choice has on attitudes to the social safety net. Last, we include simulation results on real and generated data. A software implementation is available in the R package grf. Supplementary materials for this article are available online.
DOI: --
发表时间: 2003
期刊: Social Science Research Network
影响因子: --
作者:
J. Heckman;L. Lochner;Petra E. Todd
通讯作者: Petra E. Todd
一般社会调查
DOI: --
发表时间: 2021
期刊: The Encyclopedia of Research Methods in Criminology and Criminal Justice
影响因子: --
作者:
Tom W. Smith
通讯作者: Tom W. Smith
特定案例的随机森林
DOI: --
发表时间: 2016
期刊:
影响因子: --
作者:
Ruo Xu;D. Nettleton;D. Nordman
通讯作者: D. Nordman
DOI: 10.1073/pnas.1510489113
发表时间: 2016-07-05
影响因子: 11.1
作者:
Athey, Susan;Imbens, Guido
通讯作者: Imbens, Guido
树增强 Cox 比例风险模型。
DOI: 10.1093/biostatistics/kxi024
发表时间: 2005
期刊: Biostatistics (Oxford, England)
影响因子: --
作者:
Su,Xiaogang;Tsai,Chih-Ling
通讯作者: Tsai,Chih-Ling