Abstract
In this paper we have discussed nonlinear econometric models with entropy objective functions. It has been shown that the selection of an entropy objective has two major advantages compared with the commonly used quadratic objective function. First of all, this objective function choice makes it possible to explicitly solve all linearly constrained models, i.e. with linear equality as well as inequality constraints. Secondly, the entropy objective derived from the entropy concept of information theory has a very nice property of only allowing changes in the variables that are of moderate size; thus the objective has one of the most valuable properties that we look for when modelling economic policy situations. In addition the objective function choice also offers attractive algorithmic features, i.e. the possibility to use fast and easily implemented solution methods with only small storage requirements.
This work was supported, in part, by the Natural Sciences and Engineering Research Council of Canada under grant number A8523 which is gratefully acknowledged.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Bock v. Wülfingen, G. and Pauly, P. (1978): An Optimization Approach in Multiple Target Problems using Inequality Constraints: The Case Against Weighted Criterion Functions, Annals of Economic and Social Measurement, Vol. 6, pp. 613–630.
Chow, G.C. (1975): Analysis and Control of Dynamic Economic Systems. John Wiley & Sons, New York.
Drud, A. and Meeraus, A. (1980): CONOPT — A System for Large Scale Dynamic Nonlinear Optimization — User's Manual, Version 0.105. Development Research Center, World Bank, Washington, D.C.
Eiselt, H.A., Pederzoli, G. and Sandblom, C.L. (1984): Continuous Optimization Models, Walter de Gruyter & Co., Berlin-New York.
Eriksson, O., Hallefjord, A. and Jörnsten, K. (1982): A Long Range Planning Problem with Multiple Objectives, Report LiTH-MAT-R-82-33, Linköping Institute of Technology, Linköping, Sweden.
Eriksson, J. (1980): A Note on Solution of Large Sparse Maximum Entropy Problems with Linear Equality Constraints, Mathematical Programming, Vol. 18, pp. 146–154.
Erlander, S. (1981): Entropy in Linear Programs, Mathematical Programming, Vol. 21, pp. 137–151.
Hallefjord, A. and Jörnsten, K. (1982): An Entropy Approach to Multiobjective Programming, Report LiTH-MAT-R-82-13, Linköping Institute of Technology, Linköping, Sweden.
Jörnsten, K. and Sandblom, C.L. (1982): Optimization of Economic Systems using Nonlinear Decomposition, Report LiTH-MAT-R-82-28, Linköping Institute of Technology, Linköping, Sweden, and in Journal of Information and Optimization Sciences, 1984.
Livesey, D.A. (1973): Can Macro-Economic Planning Problems Ever be Treated as a Quadratic Regulator Problem?. Proceedings of the IFAC/IFORS International Conference on Dynamic Modelling and Control of National Economies, pp. 1–14.
Sandblom, C.L. (1977): Optimization of Economic Policy using Lagged Controls, Journal of Cybernetics, Vol. 7, pp. 257–267.
Sandblom, C.L., Banasik, J.L. and Parlar, M. (1981): Economic Policy with Bounded Controls, Department of Quantitative Methods, Concordia University, Montreal.
Simon, H.A. (1956): Dynamic Programming under Uncertainty with a Quadratic Criterion Function, Econometrica, Vol. 24, pp. 74–81.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1984 Springer-Verlag
About this paper
Cite this paper
Jörnsten, K.O., Sandblom, C.L. (1984). A nonlinear econometric model with bounded controls and an entropy objective. In: Thoft-Christensen, P. (eds) System Modelling and Optimization. Lecture Notes in Control and Information Sciences, vol 59. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0008884
Download citation
DOI: https://doi.org/10.1007/BFb0008884
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-13185-4
Online ISBN: 978-3-540-38828-9
eBook Packages: Springer Book Archive