2005/02/01 by Hannes Leeb, Benedikt M. Pötscher
Engineering · Mathematics · #Advanced Statistical Methods and Models #Artificial intelligence #Computer science #Control Systems and Identification #Econometrics #Estimator #Impossibility #Inference #Machine learning #Mathematics #Model selection #Sample (material) #Selection (genetic algorithm) #Statistical Methods and Inference #Statistics
paper · doi:10.1017/s0266466605050036
crossref issued 2005/02/01 · crossref published 2005/02/01 · crossref published-print 2005/02/01 · openalex publication_date 2005/02/01 · crossref published-online 2005/02/08 · crossref created 2005/04/25 · crossref deposited 2025/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04 · crossref indexed 2026/08/04
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.