Friday seminar: Spatial Stratified Heterogeneity: Test and Attribution

By Prof. Jinfeng Wang, Chinese Academy of Sciences, Beijing, China.


Spatial stratified heterogeneity (SSH), referring to the within-strata variance less than the between strata-variance, is ubiquitous in nature, such as ecological zones and many ecological variables. SSH may imply distinct mechanisms or parameters by strata, and suggests possible determinants of the observed process. Therefore, it should be tested at the early stage of data analysis, especially in large area studies. The q-statistic was proposed to measure the degree of SSH and to test its significance. The q value is within [0,1]: 0 if SSH is not significant, and 1 if there is a perfect SSH. The exact probability density function is derived. Besides to measure SSH, the q-statistic can be used to measure the association between two variables by measuring the consistence of the spatial distributions of the two variables, under the assumption that the spatial distributions of two variables X and Y tend to be consistent if X causes Y. The association might be either linear or nonlinear. By overlaying two explanatory variables X1 and X2 then calculating its q value to Y, the q-statistic can be used to explore the interaction between X1 and X2 to Y. The new statistic is illustrated by testing and explaining the SSH of annual NDVI in China.


Dr. Jinfeng Wang is a professor of spatial analysis at the State Key Laboratory of Resources & Environmental Information System (LREIS), under the Institute of Geographic Science and Natural Resources Research at the Chinese Academy of Sciences in Beijing. He specializes in GISci/Spatial statistics and public health.




Published Jan. 8, 2018 3:12 PM - Last modified Jan. 9, 2018 1:33 PM