Academic Journal
Gweld mewn EDS

Treatment effect estimation with observational network data using machine learning

Manylion Llyfryddiaeth
Teitl: Treatment effect estimation with observational network data using machine learning
Awduron: Emmenegger Corinne, Spohn Meta-Lina, Elmer Timon, Bühlmann Peter
Ffynhonnell: Journal of Causal Inference, Vol 13, Iss 1, Pp 591-3 (2025)
Gwybodaeth am y Cyhoeddwr: De Gruyter, 2025.
Blwyddyn Cyhoeddi: 2025
Casgliad: LCC:Mathematics
LCC:Probabilities. Mathematical statistics
Termau Pwnc: dependent data, interference, observed confounding, semiparametric inference, spillover effects, 62d20, 62g20, Mathematics, QA1-939, Probabilities. Mathematical statistics, QA273-280
Disgrifiad: Causal inference methods for treatment effect estimation usually assume independent units. However, this assumption is often questionable because units may interact, resulting in spillover effects between them. We develop augmented inverse probability weighting (AIPW) for estimation and inference of the expected average treatment effect (EATE) with observational data from a single (social) network with spillover effects. In contrast to overall effects such as the global average treatment effect, the EATE measures, in expectation and on average over all units, how the outcome of a unit is causally affected by its own treatment, marginalizing over the spillover effects from other units. We develop cross-fitting theory with plugin machine learning to obtain a semiparametric treatment effect estimator that converges at the parametric rate and asymptotically follows a Gaussian distribution. The asymptotics are developed using the dependency graph rather than the network graph, which makes explicit that we allow for spillover effects beyond immediate neighbors in the network. We apply our AIPW method to the Swiss StudentLife Study data to investigate the effect of hours spent studying on exam performance accounting for the students’ social network.
Math o Ddogfen: article
Disgrifiad Ffeil: electronic resource
Iaith: English
ISSN: 2193-3685
Relation: https://doaj.org/toc/2193-3685
DOI: 10.1515/jci-2023-0082
URL mynediad: https://doaj.org/article/25ec5c8be1584caaa3b836f9775fe7e3
Cyfeirnod: edsdoj.25ec5c8be1584caaa3b836f9775fe7e3
Cronfa ddata: Directory of Open Access Journals
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://holycross.idm.oclc.org/login?auth=cas&url=https://www.browzine.com/-~-~-21933685-~-~-10.1515/jci-2023-0082-~-~-edsdoj
    Name: EDS - BrowZine
    Category: fullText
    Text: Checking BrowZine...
    Icon: https://widgets.ebscohost.com/prod/common/branding/novelist/loading.gif
    MouseOverText: BrowZine Integration
  – Url: https://www.browzine.com/-~-~-21933685-~-~-10.1515/jci-2023-0082-~-~-edsdoj
    Name: EDS - BrowZine Direct to PDF Link
    Category: fullText
    Text: LibKey Instant PDF
    MouseOverText: LibKey Instant PDF
  – Url: https://api.unpaywall.org/v2/?doi=10.1515/jci-2023-0082?email=rscheier@holycross.edu
    Name: UnpaywallEDS
    Category: fullText
    Text: Full Text Open Access
    Icon: https://widgets.ebscohost.com/prod/common/branding/oadoiapi/open_access.png
    MouseOverText: Open Access
  – Url: https://holycross.idm.oclc.org/login?auth=cas&url=https://resolver.ebscohost.com/openurl?sid=EBSCO:edsdoj&genre=article&issn=21933685&ISBN=&volume=13&issue=1&date=20250401&spage=591&pages=591-593&title=Journal of Causal Inference&atitle=Treatment%20effect%20estimation%20with%20observational%20network%20data%20using%20machine%20learning&aulast=Emmenegger%20Corinne&id=DOI:10.1515/jci-2023-0082
    Name: Full Text Finder for EDS (all content)
    Category: fullText
    Text:
    Icon: https://hcapps.holycross.edu/hcs/branding/images/icons/New-FTF-Icon-101-X-15_0.png
    MouseOverText: Check for Full Text!
Header DbId: edsdoj
DbLabel: Directory of Open Access Journals
An: edsdoj.25ec5c8be1584caaa3b836f9775fe7e3
RelevancyScore: 1069
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1069.08959960938
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Treatment effect estimation with observational network data using machine learning
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Emmenegger+Corinne%22">Emmenegger Corinne</searchLink><br /><searchLink fieldCode="AR" term="%22Spohn+Meta-Lina%22">Spohn Meta-Lina</searchLink><br /><searchLink fieldCode="AR" term="%22Elmer+Timon%22">Elmer Timon</searchLink><br /><searchLink fieldCode="AR" term="%22Bühlmann+Peter%22">Bühlmann Peter</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Journal of Causal Inference, Vol 13, Iss 1, Pp 591-3 (2025)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: De Gruyter, 2025.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: LCC:Mathematics<br />LCC:Probabilities. Mathematical statistics
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22dependent+data%22">dependent data</searchLink><br /><searchLink fieldCode="DE" term="%22interference%22">interference</searchLink><br /><searchLink fieldCode="DE" term="%22observed+confounding%22">observed confounding</searchLink><br /><searchLink fieldCode="DE" term="%22semiparametric+inference%22">semiparametric inference</searchLink><br /><searchLink fieldCode="DE" term="%22spillover+effects%22">spillover effects</searchLink><br /><searchLink fieldCode="DE" term="%2262d20%22">62d20</searchLink><br /><searchLink fieldCode="DE" term="%2262g20%22">62g20</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematics%22">Mathematics</searchLink><br /><searchLink fieldCode="DE" term="%22QA1-939%22">QA1-939</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilities%2E+Mathematical+statistics%22">Probabilities. Mathematical statistics</searchLink><br /><searchLink fieldCode="DE" term="%22QA273-280%22">QA273-280</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Causal inference methods for treatment effect estimation usually assume independent units. However, this assumption is often questionable because units may interact, resulting in spillover effects between them. We develop augmented inverse probability weighting (AIPW) for estimation and inference of the expected average treatment effect (EATE) with observational data from a single (social) network with spillover effects. In contrast to overall effects such as the global average treatment effect, the EATE measures, in expectation and on average over all units, how the outcome of a unit is causally affected by its own treatment, marginalizing over the spillover effects from other units. We develop cross-fitting theory with plugin machine learning to obtain a semiparametric treatment effect estimator that converges at the parametric rate and asymptotically follows a Gaussian distribution. The asymptotics are developed using the dependency graph rather than the network graph, which makes explicit that we allow for spillover effects beyond immediate neighbors in the network. We apply our AIPW method to the Swiss StudentLife Study data to investigate the effect of hours spent studying on exam performance accounting for the students’ social network.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic resource
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2193-3685
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://doaj.org/toc/2193-3685
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1515/jci-2023-0082
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/25ec5c8be1584caaa3b836f9775fe7e3" linkWindow="_blank">https://doaj.org/article/25ec5c8be1584caaa3b836f9775fe7e3</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsdoj.25ec5c8be1584caaa3b836f9775fe7e3
PLink https://holycross.idm.oclc.org/login?auth=cas&url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsdoj&AN=edsdoj.25ec5c8be1584caaa3b836f9775fe7e3
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1515/jci-2023-0082
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 3
        StartPage: 591
    Subjects:
      – SubjectFull: dependent data
        Type: general
      – SubjectFull: interference
        Type: general
      – SubjectFull: observed confounding
        Type: general
      – SubjectFull: semiparametric inference
        Type: general
      – SubjectFull: spillover effects
        Type: general
      – SubjectFull: 62d20
        Type: general
      – SubjectFull: 62g20
        Type: general
      – SubjectFull: Mathematics
        Type: general
      – SubjectFull: QA1-939
        Type: general
      – SubjectFull: Probabilities. Mathematical statistics
        Type: general
      – SubjectFull: QA273-280
        Type: general
    Titles:
      – TitleFull: Treatment effect estimation with observational network data using machine learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Emmenegger Corinne
      – PersonEntity:
          Name:
            NameFull: Spohn Meta-Lina
      – PersonEntity:
          Name:
            NameFull: Elmer Timon
      – PersonEntity:
          Name:
            NameFull: Bühlmann Peter
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 21933685
          Numbering:
            – Type: volume
              Value: 13
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Causal Inference
              Type: main
ResultId 1