Structural Econometrics Overview

Principles

Definition

Structural econometrics is a methodological approach within econometrics that focuses on building and estimating economic models derived explicitly from underlying economic theory. It investigates the structural relationships and causal mechanisms that generate observed data by specifying functional forms and behavioral equations based on theoretical principles, allowing for the estimation of fundamental parameters and enabling counterfactual analysis and policy evaluation grounded in economic structure.

Ontological type

Core Methods

Identification Strategies

Policy and Counterfactual Analysis

Key developments

Key Figures

Latent-Variable SEM era

Kenneth A. Bollen [1] is a prominent figure in the latent-variable SEM era, with affiliations at the University of North Carolina at Chapel Hill [3] and The Ohio State University [4] during this period. His papers from 1990 and 1995, 'Structural Equations with Latent Variables' [7] and 'Testing Structural Equation Models' [6], respectively, advanced explicit latent-variable measurement and formal testing of SEMs, underpinning the era's emphasis on measurement error and model fit. Jean‐Marie Dufour [2] is a leading figure in this era, with the Université de Montréal [5] as one of his institutional anchors during the period. His 1997 work 'Some Impossibility Theorems in Econometrics With Applications to Structural and Dynamic Models' [8] highlighted the limits of inference in complex latent-variable systems, shaping expectations about identification, near-identification, and power in this era.

Robust Identification in High-Dimensions era

Jordi Galí [1], affiliated with Massachusetts Institute of Technology [3] and Columbia University [4] in this era, emerged as a central figure in structural econometrics. His key contribution, exemplified by Inflation dynamics: A structural econometric analysis [7], was to advance robust identification in inflation dynamics through a structural econometric framework suitable for high-dimensional data, enabling policy-relevant counterfactuals amid misspecification. Mark Gertler [2], affiliated with Princeton University [5] and Boston University [6] in this era, contributed to expanding the reach of structural econometrics in macro. His contributions, as reflected in Inflation dynamics: A structural econometric analysis [7], helped anchor robust identification in macro models and informed policy-relevant counterfactuals under limited instruments.

Sign-Restricted Dynamic SEM era

Marko Sarstedt [1] is associated with Ludwig-Maximilians-Universität München [3] and University of Newcastle Australia [4] in this era. His key contributions include When to use and how to report the results of PLS-SEM [6], Identifying and treating unobserved heterogeneity with FIMIX-PLS: part I – method [7], and Structural model robustness checks in PLS-SEM [8], which were important for credible inference and methodological transparency in sign-restricted dynamic SEM. Christian M. Ringle [2] is associated with Universität Hamburg [5] and University of Newcastle Australia [4] in this era. His contributions align with the same set of works—When to use and how to report the results of PLS-SEM [6], Identifying and treating unobserved heterogeneity with FIMIX-PLS: part I – method [7], and Structural model robustness checks in PLS-SEM [8], underscoring reporting guidance, heterogeneity handling, and robustness in PLS-SEM for this era.