# Geographic Weighted Regression (GWR)
GWR offers a localized modeling approach, fitting regression equations to each point in the DataFrame. This project delves into understanding and predicting the spatial distribution of 911 emergency calls using GWR within the ArcGIS framework.
## Project Overview
This collaborative project was conducted with fellow BS GIS students—Waleed, Rana & Afsheen— at Arid University. It was part of our Geo-Statistics assignment, where each team member explored different locations using various methodologies. My focus lay on analyzing 911 emergency call data.
## Research Focus
The central research question was: How do localized socio-demographic factors influence the spatial distribution of 911 emergency calls?
## Methodology
By leveraging Geographic Weighted Regression (GWR), this analysis aimed to unravel the complex spatial relationships between various socio-demographic, environmental, and infrastructural factors and the patterns of 911 emergency calls. The investigation included exploratory data analysis, correlation and collinearity tests, and spatial autocorrelation assessments of the GWR outputs utilizing Moran's I.
## Data Sources
- [Portland 911 calls data](link)
- [Portland Stations data](link)
- [U.S. Census Bureau American Community Survey (ACS) demographics data](link)
- [USA Admin Boundaries County Zip-code](link)
## Results and Visualizations
[... and so on]
Explore our findings and visual representations [here](https://github.com/mhwahla/GWR/tree/main/assets/51794945).
## Conclusion
The combined analyses of OLS regression and GWR provide a comprehensive understanding of the diverse factors influencing 911 emergency calls. These insights are crucial for tailored interventions, resource allocation, and strategic planning to enhance emergency services at both broader and localized geographical scales.
You can copy and paste this content into your README.md file on GitHub. Adjust the links, headings, and any other details to fit your project's actual content and structure.