Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices
Many studies have shown successful applications of the Dirichlet process mixture model (DPMM) for clustering continuous data. Beyond continuous data, in practice, one can expect to see different data types, including ordinal and nominal data. Existing DPMMs for clustering mixed-type data assume a st...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Multidisciplinary Digital Publishing Institute (MDPI)
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/113587/ http://psasir.upm.edu.my/id/eprint/113587/1/113587.pdf |
| _version_ | 1848866267855847424 |
|---|---|
| author | Burhanuddin, Nurul Afiqah Ibrahim, Kamarulzaman Zulkafli, Hani Syahida Mustapha, Norwati |
| author_facet | Burhanuddin, Nurul Afiqah Ibrahim, Kamarulzaman Zulkafli, Hani Syahida Mustapha, Norwati |
| author_sort | Burhanuddin, Nurul Afiqah |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Many studies have shown successful applications of the Dirichlet process mixture model (DPMM) for clustering continuous data. Beyond continuous data, in practice, one can expect to see different data types, including ordinal and nominal data. Existing DPMMs for clustering mixed-type data assume a strict covariance matrix structure, resulting in an overfit model. This article explores a DPMM for mixed-type data that allows the covariance matrix to differ from one cluster to another. We assume an underlying latent variable framework for ordinal and nominal data, which is then modeled jointly with the continuous data. The identifiability issue on the covariance matrix poses computational challenges, thus requiring a nonstandard inferential algorithm. The applicability and flexibility of the proposed model are illustrated through simulation examples and real data applications. |
| first_indexed | 2025-11-15T14:17:54Z |
| format | Article |
| id | upm-113587 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:17:54Z |
| publishDate | 2024 |
| publisher | Multidisciplinary Digital Publishing Institute (MDPI) |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1135872024-11-14T04:00:15Z http://psasir.upm.edu.my/id/eprint/113587/ Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices Burhanuddin, Nurul Afiqah Ibrahim, Kamarulzaman Zulkafli, Hani Syahida Mustapha, Norwati Many studies have shown successful applications of the Dirichlet process mixture model (DPMM) for clustering continuous data. Beyond continuous data, in practice, one can expect to see different data types, including ordinal and nominal data. Existing DPMMs for clustering mixed-type data assume a strict covariance matrix structure, resulting in an overfit model. This article explores a DPMM for mixed-type data that allows the covariance matrix to differ from one cluster to another. We assume an underlying latent variable framework for ordinal and nominal data, which is then modeled jointly with the continuous data. The identifiability issue on the covariance matrix poses computational challenges, thus requiring a nonstandard inferential algorithm. The applicability and flexibility of the proposed model are illustrated through simulation examples and real data applications. Multidisciplinary Digital Publishing Institute (MDPI) 2024 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/113587/1/113587.pdf Burhanuddin, Nurul Afiqah and Ibrahim, Kamarulzaman and Zulkafli, Hani Syahida and Mustapha, Norwati (2024) Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices. Symmetry, 16 (6). art. no. 712. ISSN 2073-8994; eISSN: 2073-8994 https://www.mdpi.com/2073-8994/16/6/712 10.3390/sym16060712 |
| spellingShingle | Burhanuddin, Nurul Afiqah Ibrahim, Kamarulzaman Zulkafli, Hani Syahida Mustapha, Norwati Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices |
| title | Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices |
| title_full | Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices |
| title_fullStr | Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices |
| title_full_unstemmed | Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices |
| title_short | Clustering mixed-type data via Dirichlet process mixture model with cluster-specific covariance matrices |
| title_sort | clustering mixed-type data via dirichlet process mixture model with cluster-specific covariance matrices |
| url | http://psasir.upm.edu.my/id/eprint/113587/ http://psasir.upm.edu.my/id/eprint/113587/ http://psasir.upm.edu.my/id/eprint/113587/ http://psasir.upm.edu.my/id/eprint/113587/1/113587.pdf |