Electronic Thesis/Dissertation
 

Predictive Model for Battery Electric Vehicle Range in the U.S. Market

Open Access

Predicting the suitable driving range for battery electric vehicles (BEVs) that meets regional consumer preferences is a challenge for BEV manufacturers. The purpose of this praxis is to identify key predictive factors and develop a multiple linear regression model to assist BEV manufacturers in determining the suitable BEV range for regional markets in the United States. Significant predictor variables identified for this model include average personal income, household density, density of Level 3 direct current (DC) chargers, average yearly temperature, and state. These variables contribute to a multiple linear regression model that explains 88.05% of the variance in the average BEV range in Core-Based Metropolitan Statistical Areas (CBSAs). With an R-square value exceeding the target of 70%, this model demonstrates the feasibility of using regression analysis to predict average BEV range in U.S. metropolitan areas. The model's reliability is further reinforced by a K-fold cross-validation R-square value of 85.16%. In future research, enhancements to the model's accuracy could be achieved by incorporating factors such as clean energy policy incentives and subsidies, which significantly influence BEV adoption. Additionally, the regression model can be expanded to include more metropolitan areas as new BEV registration data becomes available through the Open Vehicle Registration Initiative (Atlas Public Policy, 2022).

Author Language Keyword Date created Type of Work License
  • All rights reserved
Rights statement GW Unit Degree Advisor Committee Member(s) Persistent URL

Notice to Authors

If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.

Thumbnail Title Date Uploaded Visibility Actions
Preview of PI_gwu_0075A_16662.pdf PI_gwu_0075A_16662.pdf 2024-01-11 Open Access