No open-access location is known for this record yet.
No open-access location is known for this record yet.
This paper reports on an empirical investigation of the alternative levels of analysis at which trip generation models may be built. The analysis of variance framework was used to quantify the loss of variation due to data aggregation preceding model-building. A comparative explanatory measure, sensitive to this loss, is proposed. On this basis, the personal level model tested was found to be the most successful in explaining the between-person variation in trip-making. While this was expected, it emphasises that a comparison of coefficients of determination could be misleading if models are built at different levels of analysis. The personal and household level models were both found to be capable of estimating zonal trip generation, the personal model tested performing marginally better. Future studies should consider the use of personal level models of home-based trip generation.(a)
Loading…
Imported from OpenAlex (CC0) — nothing here is generated.