Selecting Penalty Parameters of High-Dimensional M-Estimators Using Bootstrapping after Cross Validation.
We develop a new method for selecting the penalty parameter for ℓ-penalized M-estimators in high dimensions, which we refer to as bootstrapping after cross validation. We derive rates of convergence for the corresponding ℓ-penalized M-estimator and also for the post-ℓ-penalized M-estimator, which re...
| Publicado en: | Journal of Political Economy Vol. 133; no. 10; pp. 3208 - 3249 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
University of Chicago Press
Oct2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=188309203&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 188309203 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00223808 JPE jtl: Journal of Political Economy issn: 00223808 maglogo: N pubinfo: dt: Oct2025 vid: 133 iid: 10 pid: 415 pub: University of Chicago Press artinfo: ui: 188309203 10.1086/736770 ppf: 3208 ppct: 41 formats: tig: atl: Selecting Penalty Parameters of High-Dimensional M-Estimators Using Bootstrapping after Cross Validation. aug: au: Chetverikov, Denis Sørensen, Jesper Riis-Vestergaard affil: University of California, Los Angeles University of Copenhagen su: Racial differences Statistical bootstrapping Regularization parameter Model validation Simulation methods & models Sampling errors Asymptotic analysis sug: subj: Racial differences Statistical bootstrapping Regularization parameter Model validation Simulation methods & models Sampling errors Asymptotic analysis ab: We develop a new method for selecting the penalty parameter for ℓ-penalized M-estimators in high dimensions, which we refer to as bootstrapping after cross validation. We derive rates of convergence for the corresponding ℓ-penalized M-estimator and also for the post-ℓ-penalized M-estimator, which refits the nonzero entries of the former estimator without penalty in the criterion function. We demonstrate via simulations that our methods are not dominated by cross validation in terms of estimation errors and can outperform cross validation in terms of inference. As an empirical illustration, we revisit Fryer (2019), who investigated racial differences in police use of force, and confirm his findings. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|