Implementation of Mining Algorithm for the Regression Model Based on Spatial Multicollinearity Data

The mining algorithms are studied for the regression model based on spatial multicollinearity data. The main contribution of this work includes: (1) Proposes the concept of e-multicollinearity spatial data; (2) provides a new algorithm without hypothesis of irrelevance; (3)Integrates the mining of regression model with GIS technology and other technology on spatial analysis to promote more broad application of spatial statistics; (4) Proposes new algorithm e-MCL(e-multicollinearit)algorithm. (5)implements the new algorithrm over SQL server 2000 analysis services plus GIS plateform and gives experiments and performance analysis.