A note on the generalized degrees of freedom under the L1 loss function

Xiaoli Gao, Yixin Fang

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

Generalized degrees of freedom measure the complexity of a modeling procedure; a modeling procedure is a combination of model selection and model fitting. In this manuscript, we consider two definitions of generalized degrees of freedom for a modeling procedure under the L1 loss function, and investigate the connections between those two definitions. We also propose the extended Akaike information criterion, the adaptive model selection, and the extended generalized cross-validation under the L1 loss function. Finally, we extend the results to M-estimation.

Original languageEnglish (US)
Pages (from-to)677-686
Number of pages10
JournalJournal of Statistical Planning and Inference
Volume141
Issue number2
DOIs
StatePublished - Feb 2011
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Keywords

  • Adaptive model selection
  • Covariance penalty
  • Degrees of freedom
  • Generalized cross-validation
  • Least absolute deviations
  • Modeling procedure

Fingerprint

Dive into the research topics of 'A note on the generalized degrees of freedom under the L<sub>1</sub> loss function'. Together they form a unique fingerprint.

Cite this