GeoDevelopment Observatory of Bolivia / Tools
Exploratory spatial data analysis of poverty
Is a municipality as poor as its neighbours? Spatial weights, Moran’s I and LISA clusters of multidimensional poverty.
This Colab notebook asks whether poverty in one municipality resembles poverty in its neighbours. It maps the Multidimensional Poverty Index of 2012, builds six-nearest-neighbour weights and spatial lags, and tests global and local spatial dependence. Poverty is strongly clustered (Moran’s I = 0.46, p = 0.001). The LISA map finds poverty hot spots in Pando and the Chuquisaca and Potosí valleys, low-poverty clusters around Santa Cruz, the Cochabamba valley, La Paz–El Alto and Tarija, and less poor capitals such as Sucre and Cobija surrounded by poorer municipalities.