Simulation of Econometric Models with Artificial Intelligence: A Comparative Analysis of VAR/BVAR and TVAR/LSTAR Models with R

Year 2025, Volume: 2 Issue: 50, 140 - 163, 04.01.2026

Erkin Cihangir Karataş

https://doi.org/10.35343/kosbed.1721149

Abstract

This study investigates the reliability and limitations of artificial intelligence (xAI Grok-3) in econometric modelling. Using annual Chinese data for 2000–2022 (23 observations), the relationship between economic growth (constant 2015 USD GDP) and the population without access to safely managed drinking water (SWP) is examined within a Granger causality framework. The same real dataset is estimated first in the Grok-3 environment and then in R using VAR, BVAR, TVAR, and LSTAR models. No synthetic data were generated; only the processing of identical real data in two different environments is compared. Results show that Grok-simulations are highly consistent with R estimations in linear (VAR, BVAR) and threshold (TVAR) models, but exhibit significant deviations in the smooth-transition LSTAR model. Grok-3 is not yet a fully reliable econometric tool, yet it provides valuable preliminary insights for linear and semi-nonlinear specifications.

Keywords

VAR/BVAR/TVAR/LSTAR , Artificial Intelligence , Econometric Modelling , Granger Causality , Time Series Analysis

Ekonometrik Modellerin Yapay Zeka ile Simülasyonu VARBVAR ve TVARLSTAR Modellerinin R ile Karşılaştırmalı Analizi

Abstract

Bu çalışma, yapay zekanın (xAI Grok-3) ekonometrik modelleme sürecindeki güvenilirliğini ve sınırlarını incelemektedir. 2000-2022 dönemi Çin verileri (yıllık 23 gözlem) kullanılarak ekonomik büyüme (sabit 2015 USD GDP) ile güvenli içme suyuna erişimi olmayan nüfus oranı (SWP) arasındaki ilişki Granger nedenselliği çerçevesinde ele alınmıştır. Aynı gerçek veriler önce Grok-3 ortamında, ardından R programlama dilinde olmak üzere VAR, BVAR, TVAR ve LSTAR modelleriyle tahmin edilmiştir. Hiçbir aşamada sentetik veri üretilmemiş; yalnızca aynı verilerin iki farklı ortamda işlenmesi karşılaştırılmıştır. Sonuçlar, Grok-simülasyonunun doğrusal (VAR, BVAR) ve eşikli doğrusal olmayan (TVAR) modellerde R tahminleriyle yüksek derecede tutarlı olduğunu, ancak yumuşak geçişli LSTAR modelinde önemli sapmalar gösterdiğini ortaya koymuştur. Grok-3 henüz tam anlamıyla güvenilir bir ekonometrik araç değildir; fakat doğrusal ve yarı-doğrusal modellerde araştırmacıya değerli ön bilgiler sunabilmektedir.

Keywords

VAR/BVAR/TVAR/LSTAR , Yapay Zeka , Ekonometrik Modelleme , Granger Nedenselliği , Zaman Serisi Analizi

Ethical Statement

Çalışmada etik kurul izni gerektirecek bilgiler kullanılmamıştır. Kullanılan tüm veriler Dünya Bankası ve JMP/WASH veri tabanından elde edilen açık erişimli verilerdir.

Supporting Institution

Bu çalışmada herhangi bir fon veya destekten yararlanılmamıştır.

References

• Agrawal, A., Gans, J. S., & Goldfarb, A. (2019). Artificial intelligence: The ambiguous labor market impact of automating prediction. Journal of Economic Perspectives, 33(2), 31–50. https://doi.org/10.1257/jep.33.2.31
• Ahmad, A., Saeed, Q., Shah, S. M. U., Gondal, M. A., & Mumtaz, S. (2022). Environmental sustainability: Challenges and approaches. In M. K. Jhariya, R. S. Meena, A. Banerjee, & S. N. Meena (Eds.), Natural resources conservation and advances for sustainability (pp. 243–270). Elsevier. https://doi.org/10.1016/B978-0-12-822976-7.00019-3
• Alshater, M. M., Kampouris, I., Marashdeh, H., Atayah, F. O., & Banna, H. (2025). Early warning system to predict energy prices: The role of artificial intelligence and machine learning. Annals of Operations Research, 345, 1297–1333. https://doi.org/10.1007/s10479-022-04908-9
• Ashraf, F. M., Kakolu, S., & Muhammad, A. (2021). Enhancing financial forecasting accuracy through AI-driven predictive analytics models. Iconic Research and Engineering Journals, 4(12), 322–328. https://doi.org/10.1080/23311975.2025.2495191
• Athey, S., & Imbens, G. W. (2019). Machine learning methods that economists should know about. Annual Review of Economics, 11, 685–725. https://doi.org/10.1146/annurev-economics-080217-053433
• Balke, N. S. (2000). Credit and economic activity: Credit regimes and nonlinear propagation of shocks. Review of Economics and Statistics, 82(2), 344–349.
• Barbier, E. B. (2004). Water and economic growth. Economic Record, 80(248), 1–16. https://doi.org/10.1111/j.1475-4932.2004.00121.x
• Brynjolfsson, E., Li, D., & Raymond, L. R. (2023). Generative AI at work (NBER Working Paper No. 31161). National Bureau of Economic Research. https://doi.org/10.3386/w31161
• Callanan, E., Mbakwe, A., Papadimitriou, A., Pei, Y., Sibue, M., Zhu, X., Ma, Z., Liu, X., & Shah, S. (2024). Can GPT models be financial analysts? An evaluation of ChatGPT and GPT-4 on mock CFA exams. In Proceedings of the Joint Workshop of the 8th Financial Technology and Natural Language Processing (FinNLP) and the 1st Agent AI for Scenario Planning (AgentScen) (pp. 23–32), Jeju, South Korea.
• Challoumis, C. (2024). How can AI predict economic trends in the money cycle? In XVII. International Scientific Conference [Evolution] (pp. 76–108).
• Doan, T., Litterman, R., & Sims, C. (1984). Forecasting and conditional projection using realistic prior distributions. Econometric Reviews, 3(1), 1–100. https://doi.org/10.1080/07474938408800053
• Escribano, A., & Jordá, Ó. (2001). Testing nonlinearity: Decision rules for selecting between logistic and exponential STAR models. Spanish Economic Review, 3(3), 193–209. https://doi.org/10.1007/PL00011442
• Faheem, M. A., Aslam, M., & Kakolu, S. (2021). Enhancing financial forecasting accuracy through AI-driven predictive analytics models. Iconic Research and Engineering Journals, 4(12), 322–328. https://doi.org/10.13140/RG.2.2.36214.20800
• Giannone, D., Lenza, M., & Primiceri, G. E. (2015). Prior selection for vector autoregressions. Review of Economics and Statistics, 97(2), 412–435. https://doi.org/10.1162/REST_a_00483
• Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial networks. Advances in Neural Information Processing Systems, 27. https://doi.org/10.48550/arXiv.1406.2661
• Hai, D. H., & Van Tuan, P. (2024). AI and econometric modeling: Deep reinforcement learning in predictive modeling. In V. Kreinovich, W. Yamaka, & S. Leurcharusmee (Eds.), Applications of optimal transport to economics and related topics (pp. 53–60). Springer. https://doi.org/10.1007/978-3-031-67770-0_5
• Haider, S., Rashid, M., Tariq, M. A. U. R., & Nadeem, A. (2024). The role of artificial intelligence (AI) and ChatGPT in water resources. Discover Water, 4, Article 113. https://doi.org/10.1007/s43832-024-00173-y
• Hao, Y., Hu, X., & Chen, H. (2019). On the relationship between water use and economic growth in China. Journal of Cleaner Production, 235, 953–965. https://doi.org/10.1016/j.jclepro.2019.07.024
• Hubrich, K., & Teräsvirta, T. (2013). Thresholds and smooth transitions in vector autoregressive models. In VAR models in macroeconomics (pp. 273–326). https://doi.org/10.1108/S0731-9053(2013)0000031008
• Joint Monitoring Programme for Water Supply, Sanitation and Hygiene Data. (n.d.). Household data – China 2000–2022 drinking water service levels. https://washdata.org/data/household#!/(Erişim tarihi: 12 Nisan 2025)
• Josyula, H. P., Landge, S. R., Gunturu, S. R., Gupta, K., & Kiruthiga, T. (2024). Leveraging AI and ML to automate financial predictions and recommendations. In 2nd International Conference on Disruptive Technologies (ICDT) (pp. 452–457). https://doi.org/10.1109/ICDT61202.2024.10489718
• Koop, G. (2013). Forecasting with medium and large Bayesian VARs. Journal of Applied Econometrics, 28(2), 177–203. https://doi.org/10.1002/jae.1270
• Koop, G., & Korobilis, D. (2010). Bayesian multivariate time series methods for empirical macroeconomics. Foundations and Trends in Econometrics, 3(4), 267–358.
• Korinek, A. (2023). Language models and cognitive automation for economic research (NBER Working Paper No. 30957). https://doi.org/10.3386/w30957
• Lanne, M., & Saikkonen, P. (2011). Noncausal autoregressions for economic time series. Journal of Time Series Econometrics, 3(3), 32. https://doi.org/10.2202/1941-1928.1080
• Litterman, R. B. (1986). Forecasting with Bayesian vector autoregressions—Five years of experience. Journal of Business & Economic Statistics, 4(1), 25–38. https://doi.org/10.2307/1391384
• Liu, Y., Tan, Y., & Zhang, X. (2024). The long-term economic impact of water quality. Journal of Asian Economics, 94, 101796. https://doi.org/10.1016/j.asieco.2024.101796
• Ludwig, J., Mullainathan, S., & Rambachan, A. (2024). Large language models: An applied econometric framework (Working Paper No. 2025-10). Becker Friedman Institute. https://doi.org/10.48550/arXiv.2412.07031
• Mullainathan, S., & Spiess, J. (2017). Machine learning: An applied econometric approach. Journal of Economic Perspectives, 31(2), 87–106. https://doi.org/10.1257/jep.31.2.87
• Pindyck, R. S., & Rubinfeld, D. L. (1998). Econometric models and economic forecasts (4th ed.). McGraw-Hill.
• Stock, J. H., & Watson, M. (2001). Vector autoregressions. Journal of Economic Perspectives, 15(4), 101–115. https://doi.org/10.1257/jep.15.4.101
• Sui, Y., Hu, J., Zhang, N., & Ma, F. (2024). Exploring the dynamic equilibrium relationship between urbanization and ecological environment. Ecological Indicators, 158, 111456. https://doi.org/10.1016/j.ecolind.2023.111456
• Takahashi, T., & Mizuno, T. (2024). Generation of synthetic financial time series by diffusion models. Quantitative Finance, 25(10), 1507–1516. https://doi.org/10.48550/arXiv.2410.18897
• Teräsvirta, T. (1994). Specification, estimation, and evaluation of smooth transition autoregressive models. Journal of the American Statistical Association, 89(425), 208–218. https://doi.org/10.2307/2291217
• Teräsvirta, T., Tjøstheim, D., & Granger, C. W. J. (2010). Modelling nonlinear economic time series. Oxford University Press.
• Tong, H. (1990). Non-linear time series: A dynamical system approach. Oxford University Press.
• UNDP. (2016). Human development report 2016: Human development for everyone. United Nations Development Programme.
• World Bank. (2024). Water’s crucial role in shared prosperity and inclusive growth. https://www.worldbank.org/en/news/feature/2024/05/10/water-s-crucial-role-in-shared-prosperity-and-inclusive-growth (Erişim tarihi: 21 Kasım 2025)
• World Bank. (n.d.). GDP (constant 2015 US$) – China. https://data.worldbank.org/indicator/NY.GDP.MKTP.KD?locations=CN (Erişim tarihi: 12 Nisan 2025)
• World Bank. (n.d.). What is the difference between current and constant price series? https://datahelpdesk.worldbank.org/knowledgebase/articles/114942-what-is-the-difference-between-current-and-constan (Erişim tarihi: 12 Nisan 2025)
• Xu, L., & Veeramachaneni, K. (2018). Synthesizing tabular data using generative adversarial networks. arXiv preprint arXiv:1811.11264. https://doi.org/10.48550/arXiv.1811.11264