Methodology

Neighborhood size and local geographic variation of health and social determinants

Mohammad Ali¹ , Jin-Kyung Park¹ , Vu Dinh Thiem² , Do Gia Canh² , Michael Emch³ and John D Clemens¹

¹  International Vaccine Institute, SNU Research Park, San 4–8 Bongcheon-7 dong, Kwanak-gu, Seoul, Korea

²  National Institute of Health and Epidemiology, No. 1 Yersin Street, Hanoi, Vietnam

³  Robert Wood Johnson Foundation Health & Society Scholar, Columbia University, USA

author email corresponding author email

International Journal of Health Geographics 2005, 4:12doi:10.1186/1476-072X-4-12

Published:	1 June 2005

Abstract

Background

Spatial filtering using a geographic information system (GIS) is often used to smooth health and ecological data. Smoothing disease data can help us understand local (neighborhood) geographic variation and ecological risk of diseases. Analyses that use small neighborhood sizes yield individualistic patterns and large sizes reveal the global structure of data where local variation is obscured. Therefore, choosing an optimal neighborhood size is important for understanding ecological associations with diseases. This paper uses Hartley's test of homogeneity of variance (F_max) as a methodological solution for selecting optimal neighborhood sizes. The data from a study area in Vietnam are used to test the suitability of this method.

Results

The Hartley's F_max test was applied to spatial variables for two enteric diseases and two socioeconomic determinants. Various neighbourhood sizes were tested by using a two step process to implement the F_maxtest. First the variance of each neighborhood was compared to the highest neighborhood variance (upper, F_max1) and then they were compared with the lowest neighborhood variance (lower, F_max2). A significant value of F_max1 indicates that the neighborhood does not reveal the global structure of data, and in contrast, a significant value in F_max2 implies that the neighborhood data are not individualistic. The neighborhoods that are between the lower and the upper limits are the optimal neighbourhood sizes.

Conclusion

The results of tests provide different neighbourhood sizes for different variables suggesting that optimal neighbourhood size is data dependent. In ecology, it is well known that observation scales may influence ecological inference. Therefore, selecting optimal neigborhood size is essential for understanding disease ecologies. The optimal neighbourhood selection method that is tested in this paper can be useful in health and ecological studies.