tclust: An R Package for a Trimming Approach to Cluster Analysis
Outlying data can heavily influence standard clustering methods. At the same time, clustering principles can be useful when robustifying statistical procedures. These two reasons motivate the development of feasible robust model-based clustering approaches. With this in mind, an R package for perfor...
| Format: | Article |
|---|---|
| Language: | English |
| Published: |
Foundation for Open Access Statistics
2012-04-01
|
| Series: | Journal of Statistical Software |
| Subjects: | |
| Online Access: | http://www.jstatsoft.org/v47/i12/paper |
| _version_ | 1819237574968868864 |
|---|---|
| collection | DOAJ |
| description | Outlying data can heavily influence standard clustering methods. At the same time, clustering principles can be useful when robustifying statistical procedures. These two reasons motivate the development of feasible robust model-based clustering approaches. With this in mind, an R package for performing non-hierarchical robust clustering, called tclust, is presented here. Instead of trying to “fit” noisy data, a proportion α of the most outlying observations is trimmed. The tclust package efficiently handles different cluster scatter constraints. Graphical exploratory tools are also provided to help the user make sensible choices for the trimming proportion as well as the number of clusters to search for. |
| first_indexed | 2024-12-23T13:22:30Z |
| format | Article |
| id | doaj.art-05aa065607a74a9b993592c465ffc941 |
| institution | Directory Open Access Journal |
| issn | 1548-7660 |
| language | English |
| last_indexed | 2024-12-23T13:22:30Z |
| publishDate | 2012-04-01 |
| publisher | Foundation for Open Access Statistics |
| record_format | Article |
| series | Journal of Statistical Software |
| spelling | doaj.art-05aa065607a74a9b993592c465ffc9412022-12-21T17:45:24ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602012-04-014712tclust: An R Package for a Trimming Approach to Cluster AnalysisOutlying data can heavily influence standard clustering methods. At the same time, clustering principles can be useful when robustifying statistical procedures. These two reasons motivate the development of feasible robust model-based clustering approaches. With this in mind, an R package for performing non-hierarchical robust clustering, called tclust, is presented here. Instead of trying to “fit” noisy data, a proportion α of the most outlying observations is trimmed. The tclust package efficiently handles different cluster scatter constraints. Graphical exploratory tools are also provided to help the user make sensible choices for the trimming proportion as well as the number of clusters to search for.http://www.jstatsoft.org/v47/i12/papermodel-based clusteringtrimmingheterogeneous clusters |
| spellingShingle | tclust: An R Package for a Trimming Approach to Cluster Analysis Journal of Statistical Software model-based clustering trimming heterogeneous clusters |
| title | tclust: An R Package for a Trimming Approach to Cluster Analysis |
| title_full | tclust: An R Package for a Trimming Approach to Cluster Analysis |
| title_fullStr | tclust: An R Package for a Trimming Approach to Cluster Analysis |
| title_full_unstemmed | tclust: An R Package for a Trimming Approach to Cluster Analysis |
| title_short | tclust: An R Package for a Trimming Approach to Cluster Analysis |
| title_sort | tclust an r package for a trimming approach to cluster analysis |
| topic | model-based clustering trimming heterogeneous clusters |
| url | http://www.jstatsoft.org/v47/i12/paper |