On overfitting and post-selection uncertainty assessments

On overfitting and post-selection uncertainty assessments
复制标题

关于过度拟合和选择后的不确定性评估

DOI:
10.1093/biomet/asx083
复制
发表时间:
2018
期刊:
影响因子:
2.7
通讯作者:
Martin, R
Martin, R
中科院分区:
数学2区
文献类型:
--
作者:
Hong, L;Kuffner, T A;Martin, R

文献摘要

相似文献

摘要在回归背景下,当解释变量的相关子集不确定时,通常使用数据驱动的模型选择过程。经典的线性模型理论,天真地应用于选定的子模型,可能是无效的,因为它忽略了选定的子模型对数据的依赖性。我们提供了一个解释这种现象,在过拟合,一类模型选择标准。
SummaryIn a regression context, when the relevant subset of explanatory variables is uncertain, it is common to use a data-driven model selection procedure. Classical linear model theory, applied naively to the selected submodel, may not be valid because it ignores the selected submodel’s dependence on the data. We provide an explanation of this phenomenon, in terms of overfitting, for a class of model selection criteria.