Age effects on consumer demand: an additive partially linear regression model

An additive partially linear regression model is used to estimate non-parametrically the effects of total expenditure and age in the context of Engel curves and to investigate the specification and welfare interpretation of the age effects in parametric models of consumer behaviour. Empirical analysis based on data drawn from the U.K. Family Expenditure Survey shows that modelling of the effects of age requires a more sophisticated approach than that generally adopted in parametric demand analysis. It also shows that failing to adequately capture these effects can have misleading welfare implications.