Learning Centre

Using reference models in variable selection

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Pavone, Federico
dc.contributor.author Piironen, Juho
dc.contributor.author Bürkner, Paul Christian
dc.contributor.author Vehtari, Aki
dc.date.accessioned 2023-03-15T07:10:20Z
dc.date.available 2023-03-15T07:10:20Z
dc.date.issued 2023-03
dc.identifier.citation Pavone , F , Piironen , J , Bürkner , P C & Vehtari , A 2023 , ' Using reference models in variable selection ' , Computational Statistics , vol. 38 , no. 1 , pp. 349-371 . https://doi.org/10.1007/s00180-022-01231-6 en
dc.identifier.issn 0943-4062
dc.identifier.issn 1613-9658
dc.identifier.other PURE UUID: db55206d-85d7-4fc8-b9d0-9d08a086525b
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/db55206d-85d7-4fc8-b9d0-9d08a086525b
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=85130114581&partnerID=8YFLogxK
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/102729195/SCI_Pavone_etal_Computational_Statistics_2023.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/120103
dc.description Funding Information: We thank Alejandro Catalina Feliu for help with experiments, and Academy of Finland (Grants 298742, and 313122), Finnish Center for Artificial Intelligence and Technology Industries of Finland Centennial Foundation (Grant 70007503; Artificial Intelligence for Research and Development) for partial support of this research. We also acknowledge the computational resources provided by the Aalto Science-IT project. Publisher Copyright: © 2022, The Author(s).
dc.description.abstract Variable selection, or more generally, model reduction is an important aspect of the statistical workflow aiming to provide insights from data. In this paper, we discuss and demonstrate the benefits of using a reference model in variable selection. A reference model acts as a noise-filter on the target variable by modeling its data generating mechanism. As a result, using the reference model predictions in the model selection procedure reduces the variability and improves stability, leading to improved model selection performance. Assuming that a Bayesian reference model describes the true distribution of future data well, the theoretically preferred usage of the reference model is to project its predictive distribution to a reduced model, leading to projection predictive variable selection approach. We analyse how much the great performance of the projection predictive variable is due to the use of reference model and show that other variable selection methods can also be greatly improved by using the reference model as target instead of the original data. In several numerical experiments, we investigate the performance of the projective prediction approach as well as alternative variable selection methods with and without reference models. Our results indicate that the use of reference models generally translates into better and more stable variable selection. en
dc.format.extent 23
dc.format.extent 349-371
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher SPRINGER
dc.relation.ispartofseries Computational Statistics en
dc.relation.ispartofseries Volume 38, issue 1 en
dc.rights openAccess en
dc.title Using reference models in variable selection en
dc.type A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Computer Science
dc.contributor.department Probabilistic Machine Learning
dc.contributor.department Computer Science Professors
dc.contributor.department Department of Computer Science en
dc.subject.keyword Bayesian statistics
dc.subject.keyword Model reduction
dc.subject.keyword Projection predictive approach
dc.identifier.urn URN:NBN:fi:aalto-202303152429
dc.identifier.doi 10.1007/s00180-022-01231-6
dc.type.version publishedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication