Unveiling economic patterns in Türkiye: crisis and policy regimes through TICC analysis

Date

2024-12-6

Author

Açıkgöz Dalkılıç, Bengisu

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

196
views

0
downloads

Cite This

This thesis investigates the structural and temporal dynamics of Türkiye's economy over a 35-year period (1988–2023) using the Toeplitz Inverse Covariance Clustering (TICC) algorithm. Analyzing 25 multivariate economic indicators, the study identifies seven distinct macroeconomic clusters, each representing unique economic regimes shaped by crises, policy shifts, and recovery efforts. By moving beyond the ceteris paribus assumption of traditional econometric models, this research provides a holistic perspective on the interconnectedness of economic variables and their evolving relationships over time. Key findings reveal how Türkiye’s economic trajectory is marked by periods of stability, volatility, and experimentation. The 1994 financial crisis highlights trade-employment trade-offs, while the 2001 reforms showcase stabilization driven by structural adjustments. Recent clusters capture a shift from unorthodox policies, characterized by inflationary pressures and external vulnerabilities, to a return to orthodox macroeconomic frameworks emphasizing stability and credibility. These insights offer a nuanced understanding of Türkiye’s economic behavior, illustrating how systemic interactions shape transitions between regimes. This study bridges economic heuristics with scientific rigor, using advanced computational tools to uncover latent patterns and temporal dependencies. By embracing the complexity of real-world economic systems, it provides actionable insights for policymakers, offering a transformative framework for predictive modeling and informed decision-making.

Subject Keywords

TICC, Turkish Economy, Economic Regimes, Markov Random Fields

URI

https://hdl.handle.net/11511/113061

Collections

Graduate School of Natural and Applied Sciences, Thesis