Data-driven inference for the spatial scan statistic
<p>Abstract</p> <p>Background</p> <p>Kulldorff's spatial scan statistic for aggregated area maps searches for clusters of cases without specifying their size (number of areas) or geographic location in advance. Their statistical significance is tested while adjusti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2011-08-01
|
| Series: | International Journal of Health Geographics |
| Online Access: | http://www.ij-healthgeographics.com/content/10/1/47 |
| _version_ | 1818270111885164544 |
|---|---|
| author | Duczmal Luiz H Duarte Anderson R Almeida Alexandre CL Oliveira Fernando LP Takahashi Ricardo HC |
| author_facet | Duczmal Luiz H Duarte Anderson R Almeida Alexandre CL Oliveira Fernando LP Takahashi Ricardo HC |
| author_sort | Duczmal Luiz H |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>Kulldorff's spatial scan statistic for aggregated area maps searches for clusters of cases without specifying their size (number of areas) or geographic location in advance. Their statistical significance is tested while adjusting for the multiple testing inherent in such a procedure. However, as is shown in this work, this adjustment is not done in an even manner for all possible cluster sizes.</p> <p>Results</p> <p>A modification is proposed to the usual inference test of the spatial scan statistic, incorporating additional information about the size of the most likely cluster found. A new interpretation of the results of the spatial scan statistic is done, posing a modified inference question: what is the probability that the null hypothesis is rejected for the original observed cases map with a most likely cluster of size k, taking into account only those most likely clusters of size k found under null hypothesis for comparison? This question is especially important when the p-value computed by the usual inference process is near the alpha significance level, regarding the correctness of the decision based in this inference.</p> <p>Conclusions</p> <p>A practical procedure is provided to make more accurate inferences about the most likely cluster found by the spatial scan statistic.</p> |
| first_indexed | 2024-12-12T21:05:05Z |
| format | Article |
| id | doaj.art-92d8ef242e4b43b79cd532bcd8af9711 |
| institution | Directory Open Access Journal |
| issn | 1476-072X |
| language | English |
| last_indexed | 2024-12-12T21:05:05Z |
| publishDate | 2011-08-01 |
| publisher | BMC |
| record_format | Article |
| series | International Journal of Health Geographics |
| spelling | doaj.art-92d8ef242e4b43b79cd532bcd8af97112022-12-22T00:12:02ZengBMCInternational Journal of Health Geographics1476-072X2011-08-011014710.1186/1476-072X-10-47Data-driven inference for the spatial scan statisticDuczmal Luiz HDuarte Anderson RAlmeida Alexandre CLOliveira Fernando LPTakahashi Ricardo HC<p>Abstract</p> <p>Background</p> <p>Kulldorff's spatial scan statistic for aggregated area maps searches for clusters of cases without specifying their size (number of areas) or geographic location in advance. Their statistical significance is tested while adjusting for the multiple testing inherent in such a procedure. However, as is shown in this work, this adjustment is not done in an even manner for all possible cluster sizes.</p> <p>Results</p> <p>A modification is proposed to the usual inference test of the spatial scan statistic, incorporating additional information about the size of the most likely cluster found. A new interpretation of the results of the spatial scan statistic is done, posing a modified inference question: what is the probability that the null hypothesis is rejected for the original observed cases map with a most likely cluster of size k, taking into account only those most likely clusters of size k found under null hypothesis for comparison? This question is especially important when the p-value computed by the usual inference process is near the alpha significance level, regarding the correctness of the decision based in this inference.</p> <p>Conclusions</p> <p>A practical procedure is provided to make more accurate inferences about the most likely cluster found by the spatial scan statistic.</p>http://www.ij-healthgeographics.com/content/10/1/47 |
| spellingShingle | Duczmal Luiz H Duarte Anderson R Almeida Alexandre CL Oliveira Fernando LP Takahashi Ricardo HC Data-driven inference for the spatial scan statistic International Journal of Health Geographics |
| title | Data-driven inference for the spatial scan statistic |
| title_full | Data-driven inference for the spatial scan statistic |
| title_fullStr | Data-driven inference for the spatial scan statistic |
| title_full_unstemmed | Data-driven inference for the spatial scan statistic |
| title_short | Data-driven inference for the spatial scan statistic |
| title_sort | data driven inference for the spatial scan statistic |
| url | http://www.ij-healthgeographics.com/content/10/1/47 |
| work_keys_str_mv | AT duczmalluizh datadriveninferenceforthespatialscanstatistic AT duarteandersonr datadriveninferenceforthespatialscanstatistic AT almeidaalexandrecl datadriveninferenceforthespatialscanstatistic AT oliveirafernandolp datadriveninferenceforthespatialscanstatistic AT takahashiricardohc datadriveninferenceforthespatialscanstatistic |