Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria

Defining and quantifying complexity is one of the major challenges of modern science and contemporary societies. This task is particularly critical for model selection, which is aimed at properly identifying the most adequate equations to interpret the available data. The traditional solution of equ...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Murari Andrea, Riccardo Rossi, Teddy Craciunescu
Formato: article
Lenguaje:EN
Publicado: Hindawi-Wiley 2021
Materias:
Acceso en línea:https://doaj.org/article/1bcb2024796e423b9c083749a3448a0f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:1bcb2024796e423b9c083749a3448a0f
record_format dspace
spelling oai:doaj.org-article:1bcb2024796e423b9c083749a3448a0f2021-11-15T01:20:01ZAlternative Definitions of Complexity for Practical Applications of Model Selection Criteria1099-052610.1155/2021/8887171https://doaj.org/article/1bcb2024796e423b9c083749a3448a0f2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/8887171https://doaj.org/toc/1099-0526Defining and quantifying complexity is one of the major challenges of modern science and contemporary societies. This task is particularly critical for model selection, which is aimed at properly identifying the most adequate equations to interpret the available data. The traditional solution of equating the complexity of the models to the number of their parameters is clearly unsatisfactory. Three alternative approaches are proposed in this work. The first one estimates the flexibility of the proposed models to quantify their potential to overfit. The second interprets complexity as lack of stability and is implemented by computing the variations in the predictions due to uncertainties in their parameters. The third alternative is focused on assessing the consistency of extrapolation of the candidate models. All the upgrades are easy to implement and typically outperform the traditional versions of model selection criteria and constitute a good set of alternatives to be deployed, depending on the priorities of the investigators and the characteristics of the application.Murari AndreaRiccardo RossiTeddy CraciunescuHindawi-WileyarticleElectronic computers. Computer scienceQA75.5-76.95ENComplexity, Vol 2021 (2021)
institution DOAJ
collection DOAJ
language EN
topic Electronic computers. Computer science
QA75.5-76.95
spellingShingle Electronic computers. Computer science
QA75.5-76.95
Murari Andrea
Riccardo Rossi
Teddy Craciunescu
Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria
description Defining and quantifying complexity is one of the major challenges of modern science and contemporary societies. This task is particularly critical for model selection, which is aimed at properly identifying the most adequate equations to interpret the available data. The traditional solution of equating the complexity of the models to the number of their parameters is clearly unsatisfactory. Three alternative approaches are proposed in this work. The first one estimates the flexibility of the proposed models to quantify their potential to overfit. The second interprets complexity as lack of stability and is implemented by computing the variations in the predictions due to uncertainties in their parameters. The third alternative is focused on assessing the consistency of extrapolation of the candidate models. All the upgrades are easy to implement and typically outperform the traditional versions of model selection criteria and constitute a good set of alternatives to be deployed, depending on the priorities of the investigators and the characteristics of the application.
format article
author Murari Andrea
Riccardo Rossi
Teddy Craciunescu
author_facet Murari Andrea
Riccardo Rossi
Teddy Craciunescu
author_sort Murari Andrea
title Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria
title_short Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria
title_full Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria
title_fullStr Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria
title_full_unstemmed Alternative Definitions of Complexity for Practical Applications of Model Selection Criteria
title_sort alternative definitions of complexity for practical applications of model selection criteria
publisher Hindawi-Wiley
publishDate 2021
url https://doaj.org/article/1bcb2024796e423b9c083749a3448a0f
work_keys_str_mv AT murariandrea alternativedefinitionsofcomplexityforpracticalapplicationsofmodelselectioncriteria
AT riccardorossi alternativedefinitionsofcomplexityforpracticalapplicationsofmodelselectioncriteria
AT teddycraciunescu alternativedefinitionsofcomplexityforpracticalapplicationsofmodelselectioncriteria
_version_ 1718428910130036736