Dynamic Asymptotically Ideal Models and Finite Approximation
- 1 October 1997
- journal article
- research article
- Published by Taylor & Francis in Journal of Business & Economic Statistics
- Vol. 15 (4) , 482-492
Abstract
We extend Barnett and Jonas's asymptotically ideal model (AIM) to model for the possibility that the data were generated by a dynamic process. Prediction errors for dynamic and static AIM models are compared for various simulated datasets. Monetary data are also used to evaluate the AIM specifications. There is substantial evidence that an AR(1) correction considerably improves the quality of low-order finite approximations of AIM with the cost of estimating only one additional parameter. Furthermore, restricting a dynamic AIM to approximate only linear homogenous functions often results in severe misspecification.Keywords
This publication has 28 references indexed in Scilit:
- Money-Demand Variability: A Demand-Systems ApproachJournal of Business & Economic Statistics, 1992
- The Demand for Divisia Money in the United States: A Dynamic Flexible Demand SystemJournal of Money, Credit and Banking, 1991
- Translog Flexible Functional Forms and Substitutability of Monetary AssetsJournal of Business & Economic Statistics, 1988
- The Global Properties of the Minflex Laurent, Generalized Leontief, and Translog Flexible Functional FormsEconometrica, 1985
- Estimating substitution elasticities with the Fourier cost functionJournal of Econometrics, 1985
- An Elasticity can be Estimated Consistently without a Priori Knowledge of Functional FormEconometrica, 1983
- New Indices of Money Supply and the Flexible Laurent Demand SystemJournal of Business & Economic Statistics, 1983
- On the Flexibility of the Translog ApproximationInternational Economic Review, 1980
- On the flexibility of flexible functional formsJournal of Econometrics, 1977
- Estimation and Hypothesis Testing in Singular Equation Systems with Autoregressive DisturbancesEconometrica, 1975