Spatial Modeling of Infant Mortality Rate In South Central Timor Regency Using GWLR Method With Adaptive Bisquare Kernel And Gaussian Kernel

Abstract

Geographically Weighted Logistic Regression (GWLR) was regression model consider the spatial factor, which could be used to analyze the IMR. The number of Infant Mortality as big as 100 cases in 2015 or 12 per 1000 live birth in South Central Timor Regency. The aim of this study was to determine the best modeling of GWLR with fixed weighting function and Adaptive Gaussian Kernel in the case of infant mortality in South Central Timor District in 2015. The response variable (Y) in this study was a case of infant mortality, while variable predictor was the percentage of neonatal first visit (KN1) (X1), the percentage of neonatal visit 3 times (Complete KN) (X2), the percentage of pregnant get Fe tablet (X3), percentage of poor families pre prosperous (X4). This was a non-reactive study, which is a measurement which individuals surveyed did not realize that they are part of a study, with analysis unit in 32 sub-districts of South Central Timor Districts. Data analysis used open source program that was Excel, R program, Quantum GIS and GWR4. The best GWLR spatial modeling with Adaptive Gaussian Kernel weighting function, a global model parameters GWLR Adaptive Gaussian Kernel weighting function obtained by g (x) = 0.941086 - 0,892506X4, GWLR local models with adaptive Kernel bisquare weighting function in the 13 Districts were obtained g(x) = 𝛽0 − 𝛽0X4, factors that affect the cases of infant mortality in 13 sub-districts of South Central Timor Regency in 2015 was the percentage of poor families pre prosperous. Keywords: Kernel, Adaptive bisquare, GWLR, Infant mortality