A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe
Multivariate logistic regression models are mostly used to identify risk factors associated withthe occurrence of particular disease processes. Logistic regression models have also been used as tools for veterinary diagnosis by providing the probability of a particular disease in an individual anima...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference Paper |
| Language: | Inglés |
| Published: |
1997
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/50113 |
| _version_ | 1855528810177363968 |
|---|---|
| author | Pfeiffer, Dirk U. Duchateau, L. Kruska, Russell L. Ushewokunze-Obatolu, U. Perry, Brian D. |
| author_browse | Duchateau, L. Kruska, Russell L. Perry, Brian D. Pfeiffer, Dirk U. Ushewokunze-Obatolu, U. |
| author_facet | Pfeiffer, Dirk U. Duchateau, L. Kruska, Russell L. Ushewokunze-Obatolu, U. Perry, Brian D. |
| author_sort | Pfeiffer, Dirk U. |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Multivariate logistic regression models are mostly used to identify risk factors associated withthe occurrence of particular disease processes. Logistic regression models have also been used as tools for veterinary diagnosis by providing the probability of a particular disease in an individual animal given a set of characteristics such as diagnostic test results or other risk factors. They can also be applied to the predicition of the probability of the occurrence of future disease events. Decision making in animal disease control is constrained by cost-benefit considerations, which in turn should take into account the probability of the occurrence of particular disease events. The unit of interest in this context usually is an aggregate of spatial information such as an administrative district, province or state. With the advent of spatial databases and geographic information systems (GIS) the level of spatial aggregation can be easily controlled by the end user and is only limited by the spatial units at which the data has been collected. The relationships between various variables stored in a spatial database can be investigated and used to provide predictive tools allowing more cost-effective spatially optimised disease control. In this study a logistic regression model was developed to estimate the probability of theileriosis occurrence in Zimbabwe, and the usefulness of measures of model goodness-of-fit for decision makers was investigated. Specific attention was given to the potential of effects of spatial autocorrelation on regression coefficient estimates. |
| format | Conference Paper |
| id | CGSpace50113 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 1997 |
| publishDateRange | 1997 |
| publishDateSort | 1997 |
| record_format | dspace |
| spelling | CGSpace501132024-03-06T10:16:43Z A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe Pfeiffer, Dirk U. Duchateau, L. Kruska, Russell L. Ushewokunze-Obatolu, U. Perry, Brian D. theileriosis models epidemics Multivariate logistic regression models are mostly used to identify risk factors associated withthe occurrence of particular disease processes. Logistic regression models have also been used as tools for veterinary diagnosis by providing the probability of a particular disease in an individual animal given a set of characteristics such as diagnostic test results or other risk factors. They can also be applied to the predicition of the probability of the occurrence of future disease events. Decision making in animal disease control is constrained by cost-benefit considerations, which in turn should take into account the probability of the occurrence of particular disease events. The unit of interest in this context usually is an aggregate of spatial information such as an administrative district, province or state. With the advent of spatial databases and geographic information systems (GIS) the level of spatial aggregation can be easily controlled by the end user and is only limited by the spatial units at which the data has been collected. The relationships between various variables stored in a spatial database can be investigated and used to provide predictive tools allowing more cost-effective spatially optimised disease control. In this study a logistic regression model was developed to estimate the probability of theileriosis occurrence in Zimbabwe, and the usefulness of measures of model goodness-of-fit for decision makers was investigated. Specific attention was given to the potential of effects of spatial autocorrelation on regression coefficient estimates. 1997 2014-10-31T06:08:48Z 2014-10-31T06:08:48Z Conference Paper https://hdl.handle.net/10568/50113 en Limited Access |
| spellingShingle | theileriosis models epidemics Pfeiffer, Dirk U. Duchateau, L. Kruska, Russell L. Ushewokunze-Obatolu, U. Perry, Brian D. A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe |
| title | A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe |
| title_full | A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe |
| title_fullStr | A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe |
| title_full_unstemmed | A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe |
| title_short | A spatially predictive logistic regression model for occurrence of theileriosis outbreaks in Zimbabwe |
| title_sort | spatially predictive logistic regression model for occurrence of theileriosis outbreaks in zimbabwe |
| topic | theileriosis models epidemics |
| url | https://hdl.handle.net/10568/50113 |
| work_keys_str_mv | AT pfeifferdirku aspatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT duchateaul aspatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT kruskarusselll aspatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT ushewokunzeobatoluu aspatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT perrybriand aspatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT pfeifferdirku spatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT duchateaul spatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT kruskarusselll spatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT ushewokunzeobatoluu spatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe AT perrybriand spatiallypredictivelogisticregressionmodelforoccurrenceoftheileriosisoutbreaksinzimbabwe |