Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Nathan-Omenge/Spatial-Statistical-Analysis-of-HIV-Transmission-in-Kenya

Domain:

healthcaregeospatial

Record type:

project
Creator:
Nat
Host:
# Kenya HIV Spatial Analysis A comprehensive spatial statistical analysis of HIV infection patterns across Kenyan counties using exploratory spatial data analysis (ESDA) and spatial regression modeling. ## Project Overview This project examines the spatial distribution of HIV infections in Kenya and investigates the relationship between socioeconomic factors and HIV incidence patterns. The analysis employs spatial statistical methods to identify clustering patterns and assess spatial dependence in HIV data. ## Research Objectives 1. **Data Preparation & Description**: Process and merge HIV surveillance data with Kenya county shapefiles 2. **Exploratory Spatial Data Analysis (ESDA)**: - Create choropleth maps of HIV incidence - Compute global and local Moran's I statistics - Identify spatial clusters using LISA analysis 3. **Spatial Regression Modeling**: - Fit OLS, Spatial Lag Model (SLM), and Spatial Error Model (SEM) - Compare model performance and assess spatial dependence ## Key Findings - **Spatial Pattern**: No significant global spatial autocorrelation in HIV incidence (Moran's I = 0.0075, p = 0.363) - **LISA Clusters**: Identified distinct spatial clusters: - 13 High-High clusters (high incidence surrounded by high incidence) - 13 Low-Low clusters (low incidence surrounded by low incidence) - 8 High-Low outliers - 13 Low-High outliers - **Predictors**: Education index significantly associated with lower HIV incidence (β = -2892.6, p = 0.032) - **Model Selection**: OLS regression provided the best fit (AIC = 812.24) with no evidence of spatial dependence in residuals ## Data Sources - **HIV Data**: Kenya HIV spatial dataset with county-level metrics including: - Estimated new infections - HIV prevalence proportions - Socioeconomic indicators (poverty, education, urbanization) - Demographic factors (population density, youth unemployment) - **Spatial Data**: Kenya county boundaries from GADM (Global Administrative Areas) ## Methodology ### Spatial …

Visit

github.com