flexBART: Flexible Bayesian regression trees with categorical predictors
| Title: | flexBART: Flexible Bayesian regression trees with categorical predictors |
|---|---|
| Authors: | Deshpande, Sameer K. |
| Publication Year: | 2022 |
| Collection: | Statistics |
| Subject Terms: | Statistics - Methodology, Statistics - Machine Learning |
| More Details: | Most implementations of Bayesian additive regression trees (BART) one-hot encode categorical predictors, replacing each one with several binary indicators, one for every level or category. Regression trees built with these indicators partition the discrete set of categorical levels by repeatedly removing one level at a time. Unfortunately, the vast majority of partitions cannot be built with this strategy, severely limiting BART's ability to partially pool data across groups of levels. Motivated by analyses of baseball data and neighborhood-level crime dynamics, we overcame this limitation by re-implementing BART with regression trees that can assign multiple levels to both branches of a decision tree node. To model spatial data aggregated into small regions, we further proposed a new decision rule prior that creates spatially contiguous regions by deleting a random edge from a random spanning tree of a suitably defined network. Our re-implementation, which is available in the flexBART package, often yields improved out-of-sample predictive performance and scales better to larger datasets than existing implementations of BART. Comment: Software available at https://github.com/skdeshpande91/flexBART |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2211.04459 |
| Accession Number: | edsarx.2211.04459 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2211.04459 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20221108&spage=&pages=&title=flexBART: Flexible Bayesian regression trees with categorical predictors&atitle=flexBART%3A%20Flexible%20Bayesian%20regression%20trees%20with%20categorical%20predictors&aulast=Deshpande%2C%20Sameer%20K.&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2211.04459 RelevancyScore: 1037 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1037.18188476563 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: flexBART: Flexible Bayesian regression trees with categorical predictors – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Deshpande%2C+Sameer+K%2E%22">Deshpande, Sameer K.</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2022 – Name: Subset Label: Collection Group: HoldingsInfo Data: Statistics – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Statistics+-+Methodology%22">Statistics - Methodology</searchLink><br /><searchLink fieldCode="DE" term="%22Statistics+-+Machine+Learning%22">Statistics - Machine Learning</searchLink> – Name: Abstract Label: Description Group: Ab Data: Most implementations of Bayesian additive regression trees (BART) one-hot encode categorical predictors, replacing each one with several binary indicators, one for every level or category. Regression trees built with these indicators partition the discrete set of categorical levels by repeatedly removing one level at a time. Unfortunately, the vast majority of partitions cannot be built with this strategy, severely limiting BART's ability to partially pool data across groups of levels. Motivated by analyses of baseball data and neighborhood-level crime dynamics, we overcame this limitation by re-implementing BART with regression trees that can assign multiple levels to both branches of a decision tree node. To model spatial data aggregated into small regions, we further proposed a new decision rule prior that creates spatially contiguous regions by deleting a random edge from a random spanning tree of a suitably defined network. Our re-implementation, which is available in the flexBART package, often yields improved out-of-sample predictive performance and scales better to larger datasets than existing implementations of BART.<br />Comment: Software available at https://github.com/skdeshpande91/flexBART – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2211.04459" linkWindow="_blank">http://arxiv.org/abs/2211.04459</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2211.04459 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2211.04459 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Statistics - Methodology Type: general – SubjectFull: Statistics - Machine Learning Type: general Titles: – TitleFull: flexBART: Flexible Bayesian regression trees with categorical predictors Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Deshpande, Sameer K. IsPartOfRelationships: – BibEntity: Dates: – D: 08 M: 11 Type: published Y: 2022 |
| ResultId | 1 |