Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/64672 
Erscheinungsjahr: 
2012
Schriftenreihe/Nr.: 
cemmap working paper No. CWP17/12
Verlag: 
Centre for Microdata Methods and Practice (cemmap), London
Zusammenfassung: 
We consider estimation of a linear or nonparametric additive model in which a few coefficients or additive components are large and may be objects of substantive interest, whereas others are small but not necessarily zero. The number of small coefficients or additive components may exceed the sample size. It is not known which coefficients or components are large and which are small. The large coefficients or additive components can be estimated with a smaller mean-square error or integrated mean-square error if the small ones can be identified and the covariates associated with them dropped from the model. We give conditions under which several penalized least squares procedures distinguish correctly between large and small coefficients or additive components with probability approaching 1 as the sample size increases. The results of Monte Carlo experiments and an empirical example illustrate the benefits of our methods.
Schlagwörter: 
penalized regression
high-dimensional data
variable selection
Persistent Identifier der Erstveröffentlichung: 
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
452.34 kB





Publikationen in EconStor sind urheberrechtlich geschützt.