In pursuing their case study the authors choose College Station as a sample because the city's voting districts are fairly close to neighborhood communities. The authors concluded that the neighborhood effect is heavily influenced by the distribution of voters and that the neighborhood effect is related to the issues and the publicity of the issues.
To obtain their results the GIS based spatial analysis and the address matching tools mapped individual voter distribution and voting results at the local level for referendums. Arc GIS's Ripley K function and Getis-Ord's GI* was able to find the relationship between the distribution of actual voter turn-out and the neighborhood effect.
In figure 1 each point represents an individual voter and the positive z values signal high spatial clustering where as negative z values show low spatial clustering. Figure 1 shows the spatial distribution of the actual voter turn out done through the use of address matching and voting results in the local political level. The authors remarked that the neighborhood effects had a clear impact on voter turn out especially on a controversial issue that is important to voters.
This study proves that people who talk together vote together; in other words inter-personal communications and organizationally based interactions are part of the neighborhood effect which influences voting behavior. The study shows that the voter turn out’s spatial distribution influences the geographic patterns seen in voting results.
Sui, D. Z., & Hugill, P. J. (2002). A GIS-based spatial analysis on neighborhood effects and voter turn-out: a case study in College Station, Texas. Political Geography, 21(2), 159-173. doi:https://doi.org/10.1016/S0962-6298(01)00054-3