EUVIMEDEUVIMED entdecken
Crossref

Dynamic Mode Decompositions and Vector Autoregressions

Thomas J. Sargent, Yatheesan J. Selvakumar, Ziyue Yang

International Economic Review · 2026-08 · 67 (3) · 1069-1087

DOI: 10.1111/iere.70068 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Economic Review, online erschienen am 20.03.2026. Verfasst von Thomas J. Sargent und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We establish connections between dynamic mode decompositions (DMDs), vector autoregressions, and linear state‐space models, showing that DMD provides a computationally efficient, SVD‐based estimator of low‐rank first‐order VAR projection coefficients in high‐dimensional settings. When the measurement matrix has full column rank, the recovered nonzero eigenvalues coincide with those of the underlying state transition matrix. We apply DMD to a 100‐household heterogeneous‐agent economy with complete markets and Gorman aggregation. From high‐dimensional household income and consumption panels, DMD recovers latent aggregate dynamics, and cross‐sectional loadings reveal the sharing rule governing redistribution, demonstrating DMD's capacity to extract economically meaningful structure from microeconomic panels.

Zitieren

APA

Sargent, T. J., Selvakumar, Y. J., & Yang, Z. (2026). Dynamic Mode Decompositions and Vector Autoregressions. International Economic Review, 67(3), 1069-1087. https://doi.org/10.1111/iere.70068

Vancouver

Sargent TJ, Selvakumar YJ, Yang Z. Dynamic Mode Decompositions and Vector Autoregressions. International Economic Review. 2026;67(3):1069-1087. doi:10.1111/iere.70068

BibTeX
@article{Sargent2026,
  author = {Sargent, Thomas J. and Selvakumar, Yatheesan J. and Yang, Ziyue},
  title = {Dynamic Mode Decompositions and Vector Autoregressions},
  journal = {International Economic Review},
  year = {2026},
  volume = {67},
  number = {3},
  pages = {1069--1087},
  doi = {10.1111/iere.70068}
}
Kostenlos starten →