Subject. The article investigates modern economic modeling and the problem of determining the scientific status of models in the context of methodological diversity. Objectives. The purpose is to develop a universal methodological standard for assessing the scientific rigor of economic models, using a system of formal predicates. Methods. The study employs philosophical and methodological analysis, formal predicate logic, and tools of applied econometrics. It offers the operationalization of philosophical criteria of scientific validity through a system of binary predicates, each of which is associated with a set of statistical and econometric tests. Results. The paper formulated minimum criterion of scientific validity enabling to separate models that meet basic requirements from unscientific ones; developed a hierarchy of levels of scientific rigor - from basic predictive to integral. The testing on the case of innovative models (neural network systems, machine learning ensembles, agent-oriented approaches), revealed their strengths and weaknesses. Conclusions. The proposed predicate system provides a reproducible classification of economic models, increases the transparency of their comparison and defines the areas of justified application. The findings can be used both in philosophical and methodological reflection and in the practical evaluation of models for forecasting, policy analysis, and risk management.
Keywords: modern economic modeling, logical formalization, classification of models, forecasting, methodology of science
References:
Popper K.R. The Logic of Scientific Discovery. New York, Basic Books, 1959, 479 p.
Eidlin F. The Deductive-Nomological Model of Explanation. In: Mills A.J., Durepos G., Wiebe E. (eds) Encyclopedia of Case Study Research. SAGE Publications, 2010.
Campos J., Ericsson N.R., Hendry D.F. Cointegration tests in the presence of structural breaks. Journal of Econometrics, 1996, vol. 70, iss. 1, pp. 187–220. DOI: 10.1016/0304-4076(94)01689-5
Morgan M.S. The World in the Model: How Economists Work and Think. Cambridge, Cambridge University Press, 2012, 421 p.
Grigoriadou V., Coutelieris F. Towards a categorization of scientific models. Logos Episteme, 2024, vol. 15, iss. 4, pp. 425–444. DOI: 10.5840/logos-episteme202415433
Kuorikoski J., Marchionni C. Economic models and their flexible interpretations: A philosophy of science perspective. Journal of Economic Methodology, 2024, vol. 31, iss. 4, pp. 241–248. DOI: 10.1080/1350178X.2024.2336048
Gilboa I., Postlewaite A., Samuelson L., Schmeidler D. Economic theories and their dueling interpretations. Journal of Economic Methodology, 2024, vol. 31, iss. 4, pp. 189–208. DOI: 10.1080/1350178X.2022.2142270
Sterrett S.G. Physical models and fundamental laws: Using one piece of the world to tell about another. Mind and Society, 2002, vol. 5, iss. 3, pp. 51–66. DOI: 10.1007/BF02511866
Petrunin Yu.Yu. [Artificial neural networks in economics: Mathematical tool, model or methodology?]. Vestnik Moskovskogo universiteta. Seriya 6. Ekonomika, 2024, no. 4, pp. 92–113. (In Russ.) DOI: 10.55959/MSU0130-0105-6-59-4-5 EDN: PVQWGD
Diebold F.X., Mariano R.S. Comparing predictive accuracy. Journal of Business & Economic Statistics, 1995, vol. 13, iss. 3, pp. 253–263. DOI: 10.1080/07350015.1995.10524599
Giacomini R., Rossi B. Forecast comparisons in unstable environments. Journal of Applied Econometrics, 2010, vol. 25, iss. 4, pp. 595–620. DOI: 10.1002/jae.1177
Canova F., Sala L. Back to square one: Identification issues in DSGE models. Journal of Monetary Economics, 2009, vol. 56, iss. 4, pp. 431–449. DOI: 10.1016/j.jmoneco.2009.03.014
Gneiting T., Raftery A.E. Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 2007, vol. 102, iss. 477, pp. 359–378. DOI: 10.1198/016214506000001437
Christensen G., Miguel E. Transparency, reproducibility, and the credibility of economics research. Journal of Economic Literature, 2018, vol. 56, iss. 3, pp. 920–980. DOI: 10.1257/jel.20171350
Leamer E.E. Tantalus on the Road to Asymptopia. Journal of Economic Perspectives, 2010, vol. 24, iss. 2, pp. 31–46. DOI: 10.1257/jep.24.2.31
Young C., Holsteen K. Model uncertainty and robustness: A computational framework for multimodel analysis. Sociological Methods & Research, 2017, vol. 46, iss. 1, pp. 3–40. DOI: 10.1177/0049124115610347
Camerer C.F., Dreber A., Holzmeister F. et al. Evaluating the replicability of social science experiments in Nature and Science between 2010 and 2015. Nature Human Behaviour, 2018, vol. 2, pp. 637–644. DOI: 10.1038/s41562-018-0399-z
Varian H.R. Big data: New tricks for econometrics. Journal of Economic Perspectives, 2014, vol. 28, iss. 2, pp. 3–28. DOI: 10.1257/jep.28.2.3
Mullainathan S., Spiess J. Machine learning: An applied econometric approach. Journal of Economic Perspectives, 2017, vol. 31, iss. 2, pp. 87–106. DOI: 10.1257/jep.31.2.87
Athey S.A. The Impact of Machine Learning on Economics. In: Agrawal A, Gans J, Goldfarb A. (eds) The Economics of Artificial Intelligence: an agenda. Cambridge, MA, National Bureau of Economic Research, 2018, pp. 507–547.
