Determining Geographical Causal Relationships through theDevelopment of Spatial Cluster Detection and FeatureSelection Techniques

Spatial datasets contain information relating to the locations of incidents of a disease or otherphenomena. Appropriate analysis of such datasets can reveal information about the distribution of casesof the phenomena. Areas that contain higher than expected incidence of the phenomena, given thebackground population, are of particular interest. Such clusters of cases may be affected by externalfactors. By analysing the locations of potential influences, it may be possible to establish whether acause and effect relationship is present within the dataset.This thesis describes research that has led to the development and application of cluster detection andfeature selection techniques in order to determine whether causal relationships are present withingeneric spatial datasets. The techniques are described and demonstrated, and their effectivenessestablished by testing them using synthetic datasets. The techniques are then applied to a datasetsupplied by the Welsh Leukaemia Registry that details all cases of leukaemia diagnosed in Walesbetween 1990 and 2000.[...]

MoreLess

Year of publication:	2007-01-25
Authors:	Jarvis, Paul S.
Institutions:	Welsh Enterprise Institute <Pontypridd>
Published in:	University of Glamorgan - Working Paper
Subject:	Cluster-Analyse \| cluster analysis \| Information \| information \| Beziehung \| Datensatz \| Datasets \| Bevölkerung \| population

Check Google Scholar |

More access options

In German libraries (KVK)

I need help

1 Introduction
1.1 Background
1.2 Cluster detection
1.3 Feature selection
1.4 Research Objectives
1.5 Thesis outline.
2 Literature
2.1 Potential Hazards Influencing Leukaemia Risk
2.2 Cluster Detection Literature Review
2.3 Case-Control Studies
2.4 Feature Selection Literature Review
2.5 Chapter Summary
3 The Cluster Location Analysis Procedure (CLAP)
3.1 Introduction
3.2 The Search Method
3.3 Result selection
3.4 Example Demonstration
3.5 Outputs from CLAP
3.6 Conclusion
4 Assessment of CLAP
4.1 Introduction
4.2 Generated Data
4.3 Assessment results
4.4 Alternative methods
4.5 Conclusion
5 Feature Selection
5.1 Introduction
5.2 The Genetic Algorithm Overview
5.3 The Gamma test
5.4 Gamma Test Analysis
5.5 An Alternative to the Gamma test
5.6 A Practical Application of the J-Score
5.7 CHAID
5.8 Comparison of Techniques
5.9 Conclusion
6 Determining Geographical Causal Relationships
6.1 Artificial Dataset Analysis
6.2 An Equivalent to the Leukaemia Dataset
6.3 The Leukaemia Dataset Analysis
6.4 Conclusion
7 Conclusions and Future Work
7.1 Conclusions
7.2 Contribution to Knowledge
7.3 Future Work
7.4 Final Remarks
8 References
8.1 Internet References
9 Appendices
9.1 Appendix A: Data and Results from experiments
9.2 Appendix B: Published Papers

Persistent link: https://www.econbiz.de/10009128191