Pötscher, Benedikt M. and Schneider, Ulrike (2008): Confidence sets based on penalized maximum likelihood estimators.
This is the latest version of this item.

PDF
MPRA_paper_16013.pdf Download (218kB)  Preview 
Abstract
Confidence intervals based on penalized maximum likelihood estimators such as the LASSO, adaptive LASSO, and hardthresholding are analyzed. In the knownvariance case, the finitesample coverage properties of such intervals are determined and it is shown that symmetric intervals are the shortest. The length of the shortest intervals based on the hardthresholding estimator is larger than the length of the shortest interval based on the adaptive LASSO, which is larger than the length of the shortest interval based on the LASSO, which in turn is larger than the standard interval based on the maximum likelihood estimator. In the case where the penalized estimators are tuned to possess the `sparsity property', the intervals based on these estimators are larger than the standard interval by an order of magnitude. Furthermore, a simple asymptotic confidence interval construction in the `sparse' case, that also applies to the smoothly clipped absolute deviation estimator, is discussed. The results for the knownvariance case are shown to carry over to the unknownvariance case in an appropriate asymptotic sense.
Item Type:  MPRA Paper 

Original Title:  Confidence sets based on penalized maximum likelihood estimators 
Language:  English 
Keywords:  penalized maximum likelihood, Lasso, adaptive Lasso, hardthresholding, confidence set, coverage probability, sparsity, model selection. 
Subjects:  C  Mathematical and Quantitative Methods > C1  Econometric and Statistical Methods and Methodology: General > C13  Estimation: General C  Mathematical and Quantitative Methods > C0  General > C01  Econometrics 
Item ID:  16013 
Depositing User:  Benedikt Poetscher 
Date Deposited:  05 Jul 2009 18:44 
Last Modified:  28 Sep 2019 16:38 
References:  Fan, J. & R. Li (2001): Variable selection via nonconcave penalized likelihood and its oracle properties. Journal of the American Statistical Association 96, 13481360. Frank, I. E. & J. H. Friedman (1993): A statistical view of some chemometrics regression tools (with discussion). Technometrics 35, 109148. Joshi, V. M. (1969): Admissibility of the usual confidence sets for the mean of a univariate or bivariate normal population. Annals of Mathematical Statistics 40, 10421067. Kagan, A. & A. V. Nagaev (2008): A lemma on stochastic majorization and properties of the Student distribution. Theory of Probability and its Applications 52, 160164. Knight, K. & W. Fu (2000): Asymptotics of lassotype estimators. Annals of Statistics 28, 13561378. Leeb, H. & B. M. Pötscher (2008): Sparse estimators and the oracle property, or the return of Hodges' estimator. Journal of Econometrics 142, 201211. Pötscher, B. M. (2007): Confidence sets based on sparse estimators are necessarily large. Working Paper, Department of Statistics, University of Vienna. ArXiv: 0711.1036. Pötscher, B. M. & H. Leeb (2007): On the distribution of penalized maximum likelihood estimators: the LASSO, SCAD, and thresholding. Journal of Multivariate Analysis, forthcoming. ArXiv: 0711.0660. Pötscher, B. M. & U. Schneider (2007): On the distribution of the adaptive LASSO estimator. Journal of Statistical Planning and Inference 139, 27752790. Tibshirani, R. (1996): Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B 58, 267288. Zou, H. (2006): The adaptive lasso and its oracle properties. Journal of the American Statistical Association 101, 14181429. 
URI:  https://mpra.ub.unimuenchen.de/id/eprint/16013 
Available Versions of this Item

Confidence sets based on penalized maximum likelihood estimators. (deposited 11 Jun 2008 07:29)
 Confidence sets based on penalized maximum likelihood estimators. (deposited 05 Jul 2009 18:44) [Currently Displayed]