Why Long-term Dynamic Elasticities Differ from Cross-section Elasticities?
J-L Madre, INRETS, FR; F Gardes, University of Paris I, FR
What can be derived in terms of either long or short run dynamic elasticities, from the cross-sectional analysis of heterogeneous behaviors shown through only one survey ?
Data are often lacking for a good estimation of models:
- either agregate time-series are available (e.g. from National Accounts), thus the heterogeneity between individuals cannot be taken into account,
- or a survey gives a detailed description of one point in time, but no proper information on long term dynamics.
What can be derived in terms of dynamic elasticities, from the cross-sectional analysis of heterogeneous behaviors shown through only one survey ?
Three examples can be taken according to socio-demographic variables: age, residential location and income.
The recent literature on relative income effects and social interactions can be related to the old problem of the difference between cross-section and time-series estimation. On the one hand, the distribution of consumption can be estimated from the same survey by comparing individuals who, ceteris paribus, are at different positions in the income distribution, in their residential location or life cycle. On the other hand, change in expenditure due to income changes, to moving home or to ageing can be measured for the same agent (or the same type of agent) between two periods, thus using individual time-series (or pseudo-panel) data.
Association for European Transport