Latent profile analysis of human values: What is the optimal number of clusters?
Author(s) / Creator(s)
Schmidt, Mikkel N.
Seddig, Daniel
Davidov, Eldad
Mørup, Morten
Albers, Kristoffer Jon
Bauer, Jan Michael
Glückstad, Fumiko Kano
Abstract / Description
Latent Profile Analysis (LPA) is a method to extract homogeneous clusters characterized by a common response profile. Previous works employing LPA to human value segmentation tend to select a small number of moderately homogeneous clusters based on model selection criteria such as Akaike information criterion, Bayesian information criterion and Entropy. The question is whether a small number of clusters is all that can be gleaned from the data. While some studies have carefully compared different statistical model selection criteria, there is currently no established criteria to assess if an increased number of clusters generates meaningful theoretical insights. This article examines the content and meaningfulness of the clusters extracted using two algorithms: Variational Bayesian LPA and Maximum Likelihood LPA. For both methods, our results point towards eight as the optimal number of clusters for characterizing distinctive Schwartz value typologies that generate meaningful insights and predict several external variables.
Keyword(s)
typological analysis model selection criterion Bayesian latent profile analysis clustering technique human values European social surveyPersistent Identifier
Date of first publication
2021-06-30
Journal title
Methodology
Volume
17
Issue
2
Page numbers
127–148
Publisher
PsychOpen GOLD
Publication status
publishedVersion
Review status
peerReviewed
Is version of
Citation
Schmidt, M. N., Seddig, D., Davidov, E., Mørup, M., Albers, K. J., Bauer, J. M., & Glückstad, F. K. (2021). Latent profile analysis of human values: What is the optimal number of clusters?. Methodology, 17(2), 127-148. https://doi.org/10.5964/meth.5479
-
meth.v17i2.5479.pdfAdobe PDF - 2.29MBMD5: f474675c47deafefcc19a95a2ba580c1
-
There are no other versions of this object.
-
Author(s) / Creator(s)Schmidt, Mikkel N.
-
Author(s) / Creator(s)Seddig, Daniel
-
Author(s) / Creator(s)Davidov, Eldad
-
Author(s) / Creator(s)Mørup, Morten
-
Author(s) / Creator(s)Albers, Kristoffer Jon
-
Author(s) / Creator(s)Bauer, Jan Michael
-
Author(s) / Creator(s)Glückstad, Fumiko Kano
-
PsychArchives acquisition timestamp2022-04-14T11:24:53Z
-
Made available on2022-04-14T11:24:53Z
-
Date of first publication2021-06-30
-
Abstract / DescriptionLatent Profile Analysis (LPA) is a method to extract homogeneous clusters characterized by a common response profile. Previous works employing LPA to human value segmentation tend to select a small number of moderately homogeneous clusters based on model selection criteria such as Akaike information criterion, Bayesian information criterion and Entropy. The question is whether a small number of clusters is all that can be gleaned from the data. While some studies have carefully compared different statistical model selection criteria, there is currently no established criteria to assess if an increased number of clusters generates meaningful theoretical insights. This article examines the content and meaningfulness of the clusters extracted using two algorithms: Variational Bayesian LPA and Maximum Likelihood LPA. For both methods, our results point towards eight as the optimal number of clusters for characterizing distinctive Schwartz value typologies that generate meaningful insights and predict several external variables.en_US
-
Publication statuspublishedVersion
-
Review statuspeerReviewed
-
CitationSchmidt, M. N., Seddig, D., Davidov, E., Mørup, M., Albers, K. J., Bauer, J. M., & Glückstad, F. K. (2021). Latent profile analysis of human values: What is the optimal number of clusters?. Methodology, 17(2), 127-148. https://doi.org/10.5964/meth.5479en_US
-
ISSN1614-2241
-
Persistent Identifierhttps://hdl.handle.net/20.500.12034/5705
-
Persistent Identifierhttps://doi.org/10.23668/psycharchives.6309
-
Language of contenteng
-
PublisherPsychOpen GOLD
-
Is version ofhttps://doi.org/10.5964/meth.5479
-
Is related tohttps://doi.org/10.23668/psycharchives.4948
-
Keyword(s)typological analysisen_US
-
Keyword(s)model selection criterionen_US
-
Keyword(s)Bayesian latent profile analysisen_US
-
Keyword(s)clustering techniqueen_US
-
Keyword(s)human valuesen_US
-
Keyword(s)European social surveyen_US
-
Dewey Decimal Classification number(s)150
-
TitleLatent profile analysis of human values: What is the optimal number of clusters?en_US
-
DRO typearticle
-
Issue2
-
Journal titleMethodology
-
Page numbers127–148
-
Volume17
-
Visible tag(s)Version of Recorden_US