Selection of NARX models estimated using weighted least squares method via GIC-based method and l1-norm regularization methods

Pan Qin, Ryuei Nishii, Zi Jiang Yang

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)


We investigate the model selection problem for nonlinear autoregressive with exogenous variables models estimated using the weighted least squares (WLS) method. Because WLS changes the statistical property of data under study and violates the assumptions imposed on the well-developed model evaluation and selection methods (e.g. Akaike's information criterion, Schwarz's Bayesian information criterion, and the error reduction ratio based methods), therefore, new approaches should be investigated. In this research, an information criterion based method and two l1-norm regularization methods are taken into consideration: (a) in the former method, for models estimated using WLS, we first derive an information criterion in terms of the generalized information criterion (GIC, proposed by Konishi and Kitagawa in Biometrica 83(4):875-890, 1996), which is a theoretical framework for the analysis and extension of information criteria via a statistical functional approach. Then we develop a robust selection procedure by combining the GIC-based forward stepwisemethod with Subsampling; (b) in the latter two methods, we employ the l1-norm regularization methods, including Lasso and adaptive Lasso, to select models estimated with WLS. Finally, a numerical example is given to test and compare the performance of the three methods.

Original languageEnglish
Pages (from-to)1831-1846
Number of pages16
JournalNonlinear Dynamics
Issue number3
Publication statusPublished - Nov 2012

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Aerospace Engineering
  • Ocean Engineering
  • Mechanical Engineering
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Selection of NARX models estimated using weighted least squares method via GIC-based method and l<sub>1</sub>-norm regularization methods'. Together they form a unique fingerprint.

Cite this