Skip navigation
Skip navigation

The LASSO on latent indices for regression modeling with ordinal categorical predictors

Hui, Francis; Muller, Samuel; Welsh, Alan

Description

Many applications of regression models involve ordinal categorical predictors. Two common approaches for handling ordinal predictors are to form a set of dummy variables, or employ a two stage approach where dimension reduction is first applied and then the response is regressed against the predicted latent indices. Both approaches have drawbacks, with the former running into a high-dimensional problem especially if interactions are considered, while the latter separates the prediction of the...[Show more]

dc.contributor.authorHui, Francis
dc.contributor.authorMuller, Samuel
dc.contributor.authorWelsh, Alan
dc.date.accessioned2021-01-11T00:07:06Z
dc.identifier.issn0167-9473
dc.identifier.urihttp://hdl.handle.net/1885/219263
dc.description.abstractMany applications of regression models involve ordinal categorical predictors. Two common approaches for handling ordinal predictors are to form a set of dummy variables, or employ a two stage approach where dimension reduction is first applied and then the response is regressed against the predicted latent indices. Both approaches have drawbacks, with the former running into a high-dimensional problem especially if interactions are considered, while the latter separates the prediction of the latent indices from the construction of the regression model. To overcome these challenges, a new approach called the LASSO on Latent Indices (LoLI) for handling ordinal predictors in regression is proposed, which involves jointly constructing latent indices for each or for groups of ordinal predictors and modeling the response directly as a function of these. LoLI borrows strength from the response to more accurately predict the latent indices, leading to better estimation of the corresponding effects. Furthermore, LoLI incorporates a LASSO type penalty to perform hierarchical selection, with interaction terms selected only if both parent main effects are included. Simulations show that LoLI can outperform the dummy variable and two stage approaches in selection and prediction performance. Applying LoLI to an Australian household-based panel identified three dimensions of psychosocial workplace quality (job demands, stress, and security) which affect an individual's mental health in an additive and pairwise interactive manner.
dc.description.sponsorshipThis research was supported by an Australian Research Council Discovery Project grant
dc.format.mimetypeapplication/pdf
dc.language.isoen_AU
dc.publisherElsevier
dc.rights© 2020 Elsevier B.V.
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.sourceComputational Statistics and Data Analysis
dc.subjectDimension reduction
dc.subjectFactor analysis
dc.subjectFactor variables
dc.subjectInteraction
dc.subjectLatent variables
dc.subjectModel selection
dc.titleThe LASSO on latent indices for regression modeling with ordinal categorical predictors
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume149
dc.date.issued2020
local.identifier.absfor010405 - Statistical Theory
local.identifier.ariespublicationa383154xPUB11062
local.publisher.urlhttps://www.elsevier.com/en-au
local.type.statusAccepted Version
local.contributor.affiliationHui, Francis, College of Business and Economics, ANU
local.contributor.affiliationMuller, Samuel, University of Sydney
local.contributor.affiliationWelsh, Alan, College of Business and Economics, ANU
local.description.embargo2022-09-30
local.bibliographicCitation.startpage1
local.bibliographicCitation.lastpage13
local.identifier.doi10.1016/j.csda.2020.106951
dc.date.updated2020-11-02T04:16:54Z
dcterms.accessRightsOpen Access
dc.provenancehttps://v2.sherpa.ac.uk/id/publication/27883..."The Accepted Version can be archived in an Institutional Repository. 24 Months. CC BY-NC-ND." from SHERPA/RoMEO site (as at 19/01/2020).
dc.rights.licenseCC-BY-NC-ND 4.0 license
CollectionsANU Research Publications

Download

File Description SizeFormat Image
The LASSO on latent indices for regression AAM.pdf439.19 kBAdobe PDFThumbnail


This item is licensed under a Creative Commons License Creative Commons

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator