Article ID: | iaor201113469 |
Volume: | 192 |
Issue: | 1 |
Start Page Number: | 87 |
End Page Number: | 104 |
Publication Date: | Jan 2012 |
Journal: | Annals of Operations Research |
Authors: | Wan Hong, Zhang Tonglin, Zhu Yu |
Keywords: | geography & environment, military & defence, health services, statistics: inference, statistics: distributions |
The detection of radioactive materials has become a critical issue for environmental services, public health, and national security. This paper proposes a spatial statistical method to detect and localize a hidden radioactive source. Based on a detection system of multiple radiation detectors, the statistical model assumes that the counts of radiation particles received by those detectors are spatially distributed of Poisson distribution, and each comprises a signal and a background. By considering the physical law of signal degradation with distance, the paper provides a numerical method to compute the maximum likelihood estimates of the strength and location of the source. Based on these estimates, a likelihood ratio statistic is used to test the existence of the source. Because of the special properties of the model, the test statistic does not converge asymptotically to the standard chi‐square distribution. Thus a bootstrap method is proposed to compute the