A cross-country comparison of consumer expenditure patterns
About: This article is published in European Economic Review.The article was published on 1970-03-01. It has received 117 citations till now.
Citations
More filters
01 May 1970
1,935 citations
572 citations
369 citations
TL;DR: In this article, the authors derived the aggregate consumption function associated with the linear expenditure system (LES) from simple utility maximization procedures and derived the parameter set (β, γ) of LES plus an added parameter (μ: the ratio of the subjective rate of discount to the market rate of interest).
293 citations
TL;DR: In this article, it was shown that both the additivity assumptions imply approximate linear relationships between own-price and income elasticities; under direct additivity, the ratio of own price to income elasticity was approximately constant, while under indirect additivity the sum is approximately constant.
Abstract: IN the last twenty years, the theory of utility maximisation has had extensive application as a basis for deriving empirically estimable demand equations. This method of analysing and measuring demand has tended not to use general utility functions, but rather to depend upon specifications which assume that preferences are either directly or indirectly additive. Two models in particular have been used very widely; the linear expenditure system, first applied by Stone (1954), which assumes direct additivity, and the indirect addilog model, due to Leser (1941-42) and Houthakker (1960), which assumes indirect addivity. In addition to these, the directly additive models suggested by Frisch (1959) and by Powell (1966) have found practical application in a number of contexts, as have the more recent additive dynamic models of Houthakker and Taylor (1970) and of Phlips (1972). As estimation problems have been brought under control, these models have been applied to a wide range of data for different countries and today their use is part of the standard methodology of applied demand analysis.2 In this paper, it is shown that both the additivity assumptions imply approximate linear relationships between own-price and income elasticities; under direct additivity the ratio of own-price to income elasticity is approximately constant, while under indirect additivity the sum is approximately constant. These relationships are a priori implausible and there exists no empirical evidence in their favour. Consequently, the use of models based upon either of the additivity postulates seriously distorts the measurement of those responses in which demand analysis has the greatest interest, ownprice and income elasticities. Clearly, this distortion is also at least partly to blame for the empirical rejections of additivity which have been found by several investigators.3 However, since these rejections have until now been interpreted as demonstrating the failure of additive systems to model crossprice responses, which for many practical purposes are of the second-order of importance, our result adds considerable strength and plausibility to the earlier findings. The deficiencies of additive models should thus be taken
190 citations
References
More filters
TL;DR: In this paper, a method of estimating the parameters of a set of regression equations is reported which involves application of Aitken's generalized least-squares to the whole system of equations.
Abstract: In this paper a method of estimating the parameters of a set of regression equations is reported which involves application of Aitken's generalized least-squares [1] to the whole system of equations. Under conditions generally encountered in practice, it is found that the regression coefficient estimators so obtained are at least asymptotically more efficient than those obtained by an equation-by-equation application of least squares. This gain in efficiency can be quite large if “independent” variables in different equations are not highly correlated and if disturbance terms in different equations are highly correlated. Further, tests of the hypothesis that all regression equation coefficient vectors are equal, based on “micro” and “macro” data, are described. If this hypothesis is accepted, there will be no aggregation bias. Finally, the estimation procedure and the “micro-test” for aggregation bias are applied in the analysis of annual investment data, 1935–1954, for two firms.
7,637 citations
01 May 1970
1,935 citations
1,351 citations
TL;DR: In this paper, the authors considered the problem of obtaining efficient estimates for the parameters of a system of M regression equations, where the disturbance terms of this system were assumed to be related by both serial and contemporaneous correlation.
Abstract: This paper considers the problem of obtaining efficient estimates for the parameters of a system of M regression equations. The disturbance terms of this system are assumed to be related by both serial and contemporaneous correlation. Under the further assumption that the serial correlation is a first order autoregressive process, the paper develops an estimator that is consistent and has the same asymptotic normal distribution as the Aitken estimator which assumes the covariance matrix to be known. The paper concludes with a discussion of some alternative covariance specifications and points out certain difficulties with the standard single equation procedures for handling auto-regressive schemes.
1,058 citations