Parameter-based hypothesis tests for model selection

DOI10.1016/0165-1684(95)00080-WMaRDI QIDQ1350322zbMATH OpenOpenAlexFDO

Authors J. A. Stark, W. J. Fitzgerald

Publication date 27 February 1997

Published in Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0165-1684(95)00080-w

zbMATH Keywords

Akaike's information criterionBayesian information criterionNeural networksSystem identificationModel selectionChangepoint methodsData fittingPolynomial fittingSignal modelling

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Identification in stochastic control theory (93E12)

Recommendations

• Hypothesis testing: A model selection approach
• scientific article; zbMATH DE number 849929
• Model selection by multiple test procedures
• Analysis of testing-based forward model selection
• Hypothesis Testing for Mixture Model Selection
• Bayesian model selection using test statistics
• Robust tests for model selection
• Model Selection and Testing by the MDL Principle
• Model selection confidence sets by likelihood ratio testing

Cited in

(6)

• Properties of hypothesis testing techniques and (Bayesian) model selection for exploration‐based and theory‐based (order‐restricted) hypotheses
• Model selection and validation methods for non-linear systems
• Model selection via testing: an alternative to (penalized) maximum likelihood estimators.
• Confidence sets for model selection by F -testing
• Hypothesis testing: A model selection approach
• Improved time series prediction with a new method for selection of model parameters

This page was built for publication: Parameter-based hypothesis tests for model selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1350322)