Fundamental limitations of ad hoc linear and quadratic multi-level regression models for physical systems (Q423841): Difference between revisions
From MaRDI portal
Created a new Item |
Changed an Item |
||
Property / author | |||
Property / author: Andrew J. Majda / rank | |||
Normal rank | |||
Property / author | |||
Property / author: Yuan Yuan / rank | |||
Normal rank | |||
Property / review text | |||
The main results developed in this paper are rigorous theorems demonstrating the non-physical finite time blow-up and large time instability in statistical solutions of general scalar multi-level quadratic regression models with corresponding unphysical feature of the invariant measure. Surprising intrinsic model errors due to discrete sampling errors are also shown to occur rigorously even for linear multi-level regression dynamic models. All of the theoretical results are corroborated by numerical experiments with simple models. Single level nonlinear regression strategies with physical cubic damping are shown to have significant skills on the same test problems. | |||
Property / review text: The main results developed in this paper are rigorous theorems demonstrating the non-physical finite time blow-up and large time instability in statistical solutions of general scalar multi-level quadratic regression models with corresponding unphysical feature of the invariant measure. Surprising intrinsic model errors due to discrete sampling errors are also shown to occur rigorously even for linear multi-level regression dynamic models. All of the theoretical results are corroborated by numerical experiments with simple models. Single level nonlinear regression strategies with physical cubic damping are shown to have significant skills on the same test problems. / rank | |||
Normal rank | |||
Property / reviewed by | |||
Property / reviewed by: Nicko G. Gamkrelidze / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62J02 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 60H10 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62P35 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62M10 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 65C20 / rank | |||
Normal rank | |||
Property / zbMATH DE Number | |||
Property / zbMATH DE Number: 6039428 / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
nonlinear regression models | |||
Property / zbMATH Keywords: nonlinear regression models / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
unphysical blow up | |||
Property / zbMATH Keywords: unphysical blow up / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
instability | |||
Property / zbMATH Keywords: instability / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
model errors | |||
Property / zbMATH Keywords: model errors / rank | |||
Normal rank |
Revision as of 22:17, 29 June 2023
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Fundamental limitations of ad hoc linear and quadratic multi-level regression models for physical systems |
scientific article |
Statements
Fundamental limitations of ad hoc linear and quadratic multi-level regression models for physical systems (English)
0 references
30 May 2012
0 references
The main results developed in this paper are rigorous theorems demonstrating the non-physical finite time blow-up and large time instability in statistical solutions of general scalar multi-level quadratic regression models with corresponding unphysical feature of the invariant measure. Surprising intrinsic model errors due to discrete sampling errors are also shown to occur rigorously even for linear multi-level regression dynamic models. All of the theoretical results are corroborated by numerical experiments with simple models. Single level nonlinear regression strategies with physical cubic damping are shown to have significant skills on the same test problems.
0 references
nonlinear regression models
0 references
unphysical blow up
0 references
instability
0 references
model errors
0 references