Nothing to download.
Krishna Pendakur
;
Stefan Sperlich

semiparametric estimation of consumer demand systems in real expenditure (replication data)

Microdata concerning consumer demand typically show considerable variation in real expenditures, but very little variation in prices. We propose a semiparametric strategy for the consumer demand problem in which expenditure share equations are estimated nonparametrically in the real expenditure direction and estimated parametrically (with fixed or varying coefficients) in price directions. In our model, Engel curves are unrestricted: demands may have any rank. Because the demand model is derived from a cost function, it may be restricted to satisfy integrability and used for consumer surplus calculations. Since real expenditure is unobserved, but rather estimated under the model, we face a semiparametric model with a nonparametrically generated regressor. We show efficient convergence rates for parametric and nonparametric components. We illustrate the feasibility of our proposed strategy using Canadian expenditure and price data: Engel curves display curvature which cannot be encompassed by standard parametric models. We also find that the rationality restriction of Slutsky symmetry is rejected in the fixed-coefficients model, but not in the varying-coefficients model.

Data and Resources

Suggested Citation

Pendakur, Krishna; Sperlich, Stefan (2010): Semiparametric estimation of consumer demand systems in real expenditure (replication data). Version: 1. Journal of Applied Econometrics. Dataset. http://dx.doi.org/10.15456/jae.2022319.1308866001