Aggregation of alternatives and its influence on prediction
(English)Manuscript (preprint) (Other academic)
In car type choice models, alternatives are usually grouped into categories by some of their main characteristics such as make, model, vintage, body type and/or fuel type. Each of these categories contains di erent versions of the cars that are usually not recognized in the applied literature. In this study we empirically investigate whether including the heterogeneity of these versions in the modeling does matter in estimation and prediction or not. We use detailed data on alternatives available on the market down to the versions level of each model, which enables us to account for heterogeneity in the model. We also have Swedish car registry data to represent demand. We estimate separate discrete choice models with diferent methods of correction for alternative aggregation, including nesting structure. These models are estimated based on year 2006 Swedish registry data for new cars, and predict for 2007. The results show that including heterogeneity of cars' versions in the model improves model tness but it does not necessarily improve prediction results.
Aggregate alternatives, prediction, car type choice, discrete choice modeling, clean vehicles
IdentifiersURN: urn:nbn:se:kth:diva-180340OAI: oai:DiVA.org:kth-180340DiVA: diva2:892908
QS 20162016-01-112016-01-112016-01-15Bibliographically approved