Cargando…

Intervention and Identifiability in Latent Variable Modelling

We consider the use of interventions for resolving a problem of unidentified statistical models. The leading examples are from latent variable modelling, an influential statistical tool in the social sciences. We first explain the problem of statistical identifiability and contrast it with the ident...

Descripción completa

Detalles Bibliográficos
Autores principales: Romeijn, Jan-Willem, Williamson, Jon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Netherlands 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6438491/
https://www.ncbi.nlm.nih.gov/pubmed/30996521
http://dx.doi.org/10.1007/s11023-018-9460-y
_version_ 1783407107598450688
author Romeijn, Jan-Willem
Williamson, Jon
author_facet Romeijn, Jan-Willem
Williamson, Jon
author_sort Romeijn, Jan-Willem
collection PubMed
description We consider the use of interventions for resolving a problem of unidentified statistical models. The leading examples are from latent variable modelling, an influential statistical tool in the social sciences. We first explain the problem of statistical identifiability and contrast it with the identifiability of causal models. We then draw a parallel between the latent variable models and Bayesian networks with hidden nodes. This allows us to clarify the use of interventions for dealing with unidentified statistical models. We end by discussing the philosophical and methodological import of our result.
format Online
Article
Text
id pubmed-6438491
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Springer Netherlands
record_format MEDLINE/PubMed
spelling pubmed-64384912019-04-15 Intervention and Identifiability in Latent Variable Modelling Romeijn, Jan-Willem Williamson, Jon Minds Mach (Dordr) Article We consider the use of interventions for resolving a problem of unidentified statistical models. The leading examples are from latent variable modelling, an influential statistical tool in the social sciences. We first explain the problem of statistical identifiability and contrast it with the identifiability of causal models. We then draw a parallel between the latent variable models and Bayesian networks with hidden nodes. This allows us to clarify the use of interventions for dealing with unidentified statistical models. We end by discussing the philosophical and methodological import of our result. Springer Netherlands 2018-03-30 2018 /pmc/articles/PMC6438491/ /pubmed/30996521 http://dx.doi.org/10.1007/s11023-018-9460-y Text en © The Author(s) 2018 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
spellingShingle Article
Romeijn, Jan-Willem
Williamson, Jon
Intervention and Identifiability in Latent Variable Modelling
title Intervention and Identifiability in Latent Variable Modelling
title_full Intervention and Identifiability in Latent Variable Modelling
title_fullStr Intervention and Identifiability in Latent Variable Modelling
title_full_unstemmed Intervention and Identifiability in Latent Variable Modelling
title_short Intervention and Identifiability in Latent Variable Modelling
title_sort intervention and identifiability in latent variable modelling
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6438491/
https://www.ncbi.nlm.nih.gov/pubmed/30996521
http://dx.doi.org/10.1007/s11023-018-9460-y
work_keys_str_mv AT romeijnjanwillem interventionandidentifiabilityinlatentvariablemodelling
AT williamsonjon interventionandidentifiabilityinlatentvariablemodelling