Space-Time Cluster Analysis of Invasive Meningococcal Disease
Christian J.P.A. Hoebe* , Hester de Melker†, Lodewijk Spanjaard‡, Jacob Dankert‡1, and Nico Nagelkerke†
Author affiliations: *Eastern South Limburg Municipal Public Health Service, Heerlen, the Netherlands; †National Institute of Public Health and the Environment, Bilthoven, the Netherlands; ‡Netherlands Reference Laboratory for Bacterial Meningitis, Amsterdam, the Netherlands; 1Deceased 24 January 2004.
Figure 1. The concept of space-time nearest-neighborship. Nearest-neighbors in space-time are defined as cases that are nearest-neighbors in both space and time. To define the kth nearest-neighbors in space-time, we chose the number n (e.g., n = 7; thus 7 cases [O] occurring within 15 km and 7 cases [+] occurring within 13 days) in each of the neighborhoods so that the number of cases occurring in the intersection of the two neighborhoods (⊕) equals exactly k (e.g., k = 2, the first and second nearest-neighbor in space-time). The radius is shown by the data, given a certain n. For a fixed chosen value of k, the value of n varies among cases and is found with a computer-intensive search algorithm. An example is shown of the two space-time nearest-neighbors of a given index case, by taking n = 7 at a radius of 15 km (in space), and 13 days (in time). The order is determined by increasing or decreasing the space-time intersection.
The opinions expressed by authors contributing to this journal do not necessarily reflect the opinions of the U.S. Department of Health and Human Services, the Public Health Service, the Centers for Disease Control and Prevention, or the authors' affiliated institutions. Use of trade names is for identification only and does not imply endorsement by any of the groups named above.