GeoDevelopment Observatory of Bolivia / Tools
Poverty in Bolivia: an extended EDA and ESDA
One workflow from descriptive statistics to infrastructure correlates, spatial clusters, bivariate LISA, inequality and GWR.
This Colab notebook combines exploratory and spatial data analysis of multidimensional poverty (2012). Electricity and network coverage are its strongest correlates (Spearman −0.91 and −0.89), ahead of clean cooking energy, child malnutrition and night-time lights. Poverty clusters strongly in space (Moran’s I = 0.46), and a bivariate LISA relates each municipality’s poverty to its neighbours’ lights: less poor places in bright neighbourhoods around Santa Cruz, Cochabamba and Tarija, and poor places in dark ones in La Paz, Potosí, Pando and Beni. It closes with inequality measures and a geographically weighted regression.