CV-TMLE for Nonpathwise Differentiable Target Parameters
CV-TMLE for Nonpathwise Differentiable Target Parameters
复制标题
用于非路径可微目标参数的 CV-TMLE
DOI：
10.1007/978-3-319-65304-4_25
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Alexander Luedtke
中科院分区：
文献类型：
--
作者：
M. Laan;Aurélien F. Bibaut;Alexander Luedtke
TMLE是用来构造路径可微目标参数的有效替代估计量的。许多参数是非路径可微的，如非参数模型中单点处的密度或回归曲线。在这些情况下，人们通常在特定的平滑假设下使用特定的估计量，从而有可能建立一个极限分布，从而提供统计推断。然而，这样的估计器不能适应数据密度的真正未知平滑，因此，可以很容易地被能够适应潜在的真正平滑的自适应估计器所超越。
TMLE has been developed for the construction of efficient substitution estimators of pathwise differentiable target parameters. Many parameters are nonpathwise differentiable such as a density or regression curves at a single point in a nonparametric model. In these cases one often uses a specific estimator under a specific smoothness assumptions for which it is possible to establish a limit distribution and thereby provide statistical inference. However, such estimators do not adapt to the true unknown smoothness of the data density and, as a consequence, can be easily outperformed by an adaptive estimator that is able to adapt to the underlying true smoothness.