Welcome to the UPF Digital Repository

What tears couples apart: a machine learning analysis of union dissolution in Germany

Show simple item record

dc.contributor.author Arpino, Bruno
dc.contributor.author Moglie, Marco Le
dc.contributor.author Mencarini, Letizia
dc.date.accessioned 2023-05-10T06:26:17Z
dc.date.available 2023-05-10T06:26:17Z
dc.date.issued 2021
dc.identifier.citation Arpino B, Le Moglie M, Mencarini L. What tears couples apart: a machine learning analysis of union dissolution in Germany. Demography. 2021;59(1):161-86. DOI: 10.1215/00703370-9648346
dc.identifier.issn 0070-3370
dc.identifier.uri http://hdl.handle.net/10230/56759
dc.description.abstract This study contributes to the literature on union dissolution by adopting a machine learning (ML) approach, specif­i­cally Random Survival Forests (RSF). We used RSF to analyze data on 2,038 married or cohabiting couples who participated in the German Socio-Economic Panel Survey, and found that RSF had considerably better predictive accuracy than conventional regression models. The man’s and the woman’s life satisfaction and the woman’s percentage of housework were the most important predictors of union dissolution; several other variables (e.g., woman’s working hours, being married) also showed substantial predictive power. RSF was able to detect complex patterns of association, and some predictors examined in previous studies showed marginal or null predictive power. Finally, while we found that some personality traits were strongly predictive of union dissolution, no interactions between those traits were evident, possibly reflecting assortative mating by personality traits. From a methodological point of view, the study demonstrates the potential bene­fits of ML techniques for the analysis of union dissolution and for demographic research in general. Key features of ML include the ability to handle a large number of predictors, the automatic detection of nonlinearities and nonadditivities between predictors and the outcome, generally superior predictive accuracy, and robustness against multicollinearity.
dc.description.sponsorship The research leading to these results received funding from the European Research Council, under the European ERC Grant Agreement no. StG-313617 (SWELL-FER: Subjective Well-being and Fertility; principal investigator, Letizia Mencarini).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Duke University Press
dc.relation.ispartof Demography. 2021;59(1):161-86.
dc.rights This is an open access article distributed under the terms of a Creative Commons license (CC BY-NC-ND 4.0).
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.title What tears couples apart: a machine learning analysis of union dissolution in Germany
dc.type info:eu-repo/semantics/article
dc.identifier.doi http://dx.doi.org/10.1215/00703370-9648346
dc.subject.keyword Union dissolution
dc.subject.keyword Machine learning
dc.subject.keyword Random Survival Forests
dc.subject.keyword Germany
dc.subject.keyword Socio-Economic Panel Study
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/313617
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking