Exploring geographic variations of presidential election 2016

Authors: Jun Luo*, Missouri State University
Topics: Spatial Analysis & Modeling, Geographic Information Science and Systems, Political Geography
Keywords: Geographic variations;Presidential election;Random forest algorithm;GWR;GIS
Session Type: Paper
Day: 4/10/2020
Start / End Time: 8:00 AM / 9:15 AM
Room: Tower Court B, Sheraton, IM Pei Tower, Second Floor Level
Presentation File: No File Uploaded

This paper aims to develop an analysis framework to investigate the spatial variations of presidential election of 2016 at county level. The proposed analysis framework includes two major steps. The first step is to use random forest algorithm to identify significant socioeconomic variables of population that contribute to the percentage of votes for Trump. The second step is to use geographically weighted regression to reveal the spatial variations of the explanatory variables. For each step, various assessments for the validity of the models will be conducted. The results of the project will provide insights for better understanding the geographic variations of presidential election 2016 and for the prediction for presidential election 2020. The proposed framework will also benefit researchers that study socioeconomic phenomena for which geography/space might plays an important role.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login