Revisiting Aschauer via ICM estimation

Abstract

In this article, the effect of public expenditure on consumers’ welfare is considered by estimating the substitutability of public expenditure for private consumption in the context of Aschauer (1985). Aschauer’s full information maximum likelihood estimation requires much more assumptions than the equilibrium condition of his model. Therefore, this study proposes an alternative estimation approach under a weaker condition, which is equivalent to the equilibrium condition of the model. In particular, I propose to use an integrated conditional moments estimation and apply the proposed estimation to US economy. The estimation results show that Aschauer’s model specification is not rejected at conventional significance levels, even though substitutability of public expenditure for private consumption is not significantly different from zero.

Keywords:

• integrated conditional moment
• private consumption
• public spending

JEL codes:

• C18
• C51
• E21
• H31
• H50

Acknowledgements

I am very grateful to Herman Bierens for his valuable comments. I am also grateful to Joo Yong Lee, Chirok Han, Jinseo Cho, Changsick Kim, Yoon–jae Whang and June Park for their careful comments and suggestions for the preivous versions.

Notes

¹ Equation 1 implies . Hence, . This leads to Equation 3.

² Another role of the rational expectation for G_t is that we do not have to care about the endogeneity problem any longer.

³ Unlike Graham (1993), I do not consider implementing FIML of Equations 4 and 6 in this article because of two reasons. First, it is not trivial to implement FIML because of the error term in Equation 6. Second, it still requires the correct functional form specification of G_t and parametric distributional assumption on (u, v).

⁴ Bierens (1982) and Bierens (1990) point out that the choice of weight function does not affect the consistency. In particular, Bierens and Song (2012) chooses w(t) = exp.

⁵ For details, see Theorem 7 in Bierens and Ploberger (1997).

⁶ For this reason, method of moments estimators and GMM estimators can be incorporated in ICM estimators because those estimates can be used as initial estimates in the simplex method.