Beyond the Average Elasticity – Applying Quantile Panel Regression to German Household Mobility Data

This paper employs quantile panel regression to the study of fuel price elasticities. Contrasting with standard panel approaches, this method reveals the impact of explanatory variables across all points in the conditional distribution of the response variable while controlling for unobserved heterogeneity. Applying quantile panel regression to German household data demonstrates that fuel price elasticities are very high in magnitude – below -0.8 – for a small segment of households whose car mileage is low, but that this effect tapers off rapidly among households with higher car mileage. These findings have implications for policy instruments that rely on estimates of fuel price elasticities, for example fuel taxation.