Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data
In this paper, we propose presenting a solution based on socio-epidemiological variables of tuberculosis, considering a clustering with spatial/geographical constraints; and, determine a value of alpha that increases spatial contiguity without significantly deteriorating the quality of the solution...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/8/9/1478 |
| _version_ | 1797554916250615808 |
|---|---|
| author | Dalila Camêlo Aguiar Ramón Gutiérrez Sánchez Edwirde Luiz Silva Camêlo |
| author_facet | Dalila Camêlo Aguiar Ramón Gutiérrez Sánchez Edwirde Luiz Silva Camêlo |
| author_sort | Dalila Camêlo Aguiar |
| collection | DOAJ |
| description | In this paper, we propose presenting a solution based on socio-epidemiological variables of tuberculosis, considering a clustering with spatial/geographical constraints; and, determine a value of alpha that increases spatial contiguity without significantly deteriorating the quality of the solution based on the variables of interest, i.e. those of the feature space. For the application of Ward’s hierarchical clustering method, two dissimilarity matrices were calculated, the first provides the dissimilarities in the feature space calculated from the socio-epidemiological variables <inline-formula><math display="inline"><semantics><msub><mi>D</mi><mn>0</mn></msub></semantics></math></inline-formula> and the second provides the dissimilarities in the calculated constraints space from the geographical distances <inline-formula><math display="inline"><semantics><msub><mi>D</mi><mn>1</mn></msub></semantics></math></inline-formula>, together with an <inline-formula><math display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> mixing parameter and the non-uniform weight <i>w</i> assigned to the calculation of the dissimilarity matrix defined by the standardized incidence ratio (SIR) of TB and that contributed significantly to the increase in clarity, both from a spatial and socio-epidemiological point of view. The method is shown to be feasible in epidemiological studies in the joint understanding of factors of different dimensions, aggregated from a spatial perspective. It is analysis tool that allows making a better understanding of the socio-epidemiological reality of the municipality. |
| first_indexed | 2024-03-10T16:38:53Z |
| format | Article |
| id | doaj.art-8ce5ae8c4bc44f7e92a63db69989a952 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T16:38:53Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-8ce5ae8c4bc44f7e92a63db69989a9522023-11-20T12:12:28ZengMDPI AGMathematics2227-73902020-09-0189147810.3390/math8091478Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis DataDalila Camêlo Aguiar0Ramón Gutiérrez Sánchez1Edwirde Luiz Silva Camêlo2Department of Statistics and Operational Research, Faculty of Science, University of Granada, Avda. Fuentenueva, S/N, 18071 Granada, SpainDepartment of Statistics and Operational Research, Faculty of Science, University of Granada, Avda. Fuentenueva, S/N, 18071 Granada, SpainDepartment of Statistics, State University of Paraíba, Rua Baraúnas, 351—Bairro Universitário, Campina Grande 58429-500, BrazilIn this paper, we propose presenting a solution based on socio-epidemiological variables of tuberculosis, considering a clustering with spatial/geographical constraints; and, determine a value of alpha that increases spatial contiguity without significantly deteriorating the quality of the solution based on the variables of interest, i.e. those of the feature space. For the application of Ward’s hierarchical clustering method, two dissimilarity matrices were calculated, the first provides the dissimilarities in the feature space calculated from the socio-epidemiological variables <inline-formula><math display="inline"><semantics><msub><mi>D</mi><mn>0</mn></msub></semantics></math></inline-formula> and the second provides the dissimilarities in the calculated constraints space from the geographical distances <inline-formula><math display="inline"><semantics><msub><mi>D</mi><mn>1</mn></msub></semantics></math></inline-formula>, together with an <inline-formula><math display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> mixing parameter and the non-uniform weight <i>w</i> assigned to the calculation of the dissimilarity matrix defined by the standardized incidence ratio (SIR) of TB and that contributed significantly to the increase in clarity, both from a spatial and socio-epidemiological point of view. The method is shown to be feasible in epidemiological studies in the joint understanding of factors of different dimensions, aggregated from a spatial perspective. It is analysis tool that allows making a better understanding of the socio-epidemiological reality of the municipality.https://www.mdpi.com/2227-7390/8/9/1478ward-like algorithmspatial constraintsmeasure of riskTuberculosisState of Paraíba, Brazil |
| spellingShingle | Dalila Camêlo Aguiar Ramón Gutiérrez Sánchez Edwirde Luiz Silva Camêlo Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data Mathematics ward-like algorithm spatial constraints measure of risk Tuberculosis State of Paraíba, Brazil |
| title | Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data |
| title_full | Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data |
| title_fullStr | Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data |
| title_full_unstemmed | Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data |
| title_short | Hierarchical Clustering with Spatial Constraints and Standardized Incidence Ratio in Tuberculosis Data |
| title_sort | hierarchical clustering with spatial constraints and standardized incidence ratio in tuberculosis data |
| topic | ward-like algorithm spatial constraints measure of risk Tuberculosis State of Paraíba, Brazil |
| url | https://www.mdpi.com/2227-7390/8/9/1478 |
| work_keys_str_mv | AT dalilacameloaguiar hierarchicalclusteringwithspatialconstraintsandstandardizedincidenceratiointuberculosisdata AT ramongutierrezsanchez hierarchicalclusteringwithspatialconstraintsandstandardizedincidenceratiointuberculosisdata AT edwirdeluizsilvacamelo hierarchicalclusteringwithspatialconstraintsandstandardizedincidenceratiointuberculosisdata |