Model selection and inference:: Facts and fiction

被引:386
|
作者
Leeb, H
Pötscher, BM
机构
[1] Univ Vienna, Dept Stat, A-1010 Vienna, Austria
[2] Yale Univ, New Haven, CT 06520 USA
关键词
D O I
10.1017/S0266466605050036
中图分类号
F [经济];
学科分类号
02 ;
摘要
Model selection has an important impact on subsequent inference. Ignoring the model selection step leads to invalid inference. We discuss some intricate aspects of data-driven model selection that do not seem to have been widely appreciated in the literature. We debunk some myths about model selection, in particular the myth that consistent model selection has no effect on subsequent inference asymptotically. We also discuss an "impossibility" result regarding the estimation of the finite-sample distribution of post-model-selection estimators.
引用
收藏
页码:21 / 59
页数:39
相关论文
共 50 条