spatial-epidemiology

To calculate Moran's I for disease mapping, you need a disease rate GeoDataFrame and PySAL spatial weights. The skill applies ESDA Moran computations to measure whether disease rates are spatially clustered versus randomly distributed.

LISA clustering identifies disease hotspots by detecting local spatial autocorrelation. It flags HH and LL clusters alongside HL and LH spatial outliers, producing interpretable cluster maps that show exactly where localized disease risk concentrates.

Computing Standardized Morbidity Ratios for indirect standardization requires population data across age or demographic strata. The skill calculates SMR to enable fair disease burden comparisons across geographic units with differing population structures.

The Knox test evaluates space-time clustering by checking if disease cases cluster jointly in space and time rather than independently. It processes geographic coordinates and outbreak timing to quantify space-time interaction in your dataset.

Yes, you need PySAL and libpysal installed to run permutation-based significance testing. The skill relies on these dependencies alongside geopandas, numpy, scipy, and matplotlib to compute spatial epidemiology statistics and generate geospatial plots.

The best way to generate choropleth maps for public health disease rates is using GeoPandas geospatial plotting. The skill creates choropleth maps from your computed disease mapping statistics to communicate spatial risk variations to public-health stakeholders.