# Spatial Analysis of Malaria Epidemiology in Kenya 🇰🇪
## **Project Overview**
This project conducts a **spatial econometric analysis** of malaria incidence across the **47 counties of Kenya**. By integrating epidemiological, climatic, demographic, and socio-economic variables, the study identifies statistically significant **malaria hotspots** and models the key drivers of disease transmission using a **Spatial Lag Model (SLM)**.
The findings show that malaria in Kenya is a **spatially dependent phenomenon**, influenced by rainfall patterns, ecological zones, and transmission spillover across neighboring counties.
---
## **Key Objectives**
### **1. Visualization**
* Produce choropleth maps showing malaria incidence across counties.
* Explore spatial clustering including hotspots and coldspots.
### **2. Spatial Diagnostics**
* Compute **Global Moran’s I** to assess overall clustering.
* Use **Local Indicators of Spatial Association (LISA)** to detect specific high-burden zones.
### **3. Spatial Econometric Modeling**
* Fit **Spatial Lag (SLM)** and **Spatial Error (SEM)** models.
* Test significance of climatic (rainfall, temperature), demographic (population), and socio-economic (poverty) drivers.
---
## **Data Sources**
| Dataset Type | Source | Description |
| ---------------------- | --------------------------- | --------------------------------------- |
| **Spatial Boundaries** | GADM v4.1 | Kenya county shapefiles (vector data) |
| **Epidemiology** | Ministry of Health | Malaria incidence per 1,000 population |
| **Climate** | Ecological zone simulations | Annual Rainfall (mm) & Temperature (°C) |
| **Socio-Economic** | KNBS (2022) | Poverty Headcount Index |
| **Demographics** | KNBS Projections (2025) | Population totals per county |
---
Link to data Sources :
- **Geo Data Soure**
h …