Performance Characterization of Clusterwise Linear Regression Algorithms

ABSTRACT Clusterwise linear regression (CLR) is a powerful extension of the conventional linear regression framework when the data complexity exceeds the capability of a single linear model. This article presents the first examination of CLR algorithms developed over the past two decades through ran...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Wiley interdisciplinary reviews. Computational statistics Ročník 16; číslo 5; s. e70004 - n/a
Hlavní autoři: Kuang, Ye Chow, Ooi, Melanie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Hoboken, USA John Wiley & Sons, Inc 01.09.2024
Wiley Subscription Services, Inc
Témata:
Algorithms
Regression models
ISSN:1939-5108, 1939-0068
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:ABSTRACT Clusterwise linear regression (CLR) is a powerful extension of the conventional linear regression framework when the data complexity exceeds the capability of a single linear model. This article presents the first examination of CLR algorithms developed over the past two decades through randomized large‐sample testing. Using a unified framework and carefully controlled data characteristics, a comprehensive and systematic assessment of CLR algorithms were performed. The findings of this study provide potential users with a clear understanding of the various benefits and limitations of selecting the appropriate CLR algorithms for their data. Furthermore, this study has disproved past claims which were concluded based on limited samples, and provides insights to better understand the CLR challenges. Finally, this article identifies areas for improvement that could provide crucial performance and reliability improvement of CLR algorithms.
Bibliografie:This work was supported by the University of Waikato (2022/2023 Summer Research Scholarship).
Funding
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-5108
1939-0068
DOI:10.1002/wics.70004