A maximum log-likelihood based data fusion model for estimating household’s vehicle purchase decision

Abstract

The growing adoption of electric vehicles offers a potential opportunity to reduce transportation sector carbon footprint. In our research, we studied vehicle purchase behavior with emphasis on alternative fuel vehicles using the vehicle purchase dataset ‘MaritzCX New Vehicle Customer Study.’ This study consisted of a two-level modeling approach. In the first level, purchasing of a new car was estimated based on consumers socio-economic characteristics. In the second level, the vehicle purchase decision was examined with a two-dimensional dependent variable–vehicle type and fuel type. We employed an innovative data fusion approach that probabilistically links records from MaritzCX with records from National Household Travel Survey with the objective of identifying new independent variables affecting the decision process while maximizing data fit. The final model included a host of independent variables from four different categories: vehicle-, economic-, demographic-, and spatial characteristics. Finally, the model results were employed to conduct an elasticity analysis.