Econometrics Overview

Principles

Definition

Econometrics is the quantitative analysis of economic phenomena using statistical inference and mathematical modeling to provide empirical content to economic theories and test hypotheses about economic relationships.

Ontological type

Identification Strategies

Core Methods

Model Assumptions

Key developments

Key Figures

Spectral-Structural Synthesis era

Clive W. J. Granger [1] is associated with University of California, San Diego [3] and University of Nottingham [4] in this era, shaping spectral‑structural econometrics. His contributions include Spectral Analysis of Economic Time Series [6] (1966) and Investigating Causal Relations by Econometric Models and Cross-spectral Methods [5] (1969), which advanced integration of spectral methods with econometric models and bolstered policy‑relevant forecasting. H. Smith [2] is likewise active in this era through Applied Regression Analysis [7] (1967). This line of work reinforced regression diagnostics and estimation theory that underpinned broader macroeconometric forecasting and policy simulation characteristic of the era.

Robust Dynamic Cointegration era

Søren Johansen [1], affiliated with the University of Copenhagen [3] and the European University Institute [4] during this era, stands as a central figure in the econometrics of cointegration. His key contributions in this era include the foundations laid in Statistical analysis of cointegration vectors [7], MAXIMUM LIKELIHOOD ESTIMATION AND INFERENCE ON COINTEGRATION — WITH APPLICATIONS TO THE DEMAND FOR MONEY [8], and Estimation and Hypothesis Testing of Cointegration Vectors in Gaussian Vector Autoregressive Models [9], which advanced estimation, inference, and testing for cointegration in Gaussian VAR frameworks and underpinned reliable long-run equilibrium analysis. Whitney K. Newey [2], with appointments at the Massachusetts Institute of Technology [5] and the University of California, Berkeley [6] during this period, contributed to the development of robust covariance estimation crucial for econometric inference. His sole listed paper in this era, A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix [10], introduced HAC estimators that enabled credible inference under heteroskedasticity and autocorrelation, aligning with the era's emphasis on diagnostic rigor.

Data-Rich Causal Heterogeneity era

Robert Tibshirani [1] is a leading figure in data-rich econometrics during 2000-2023, with affiliations at Harvard University [3] and the Massachusetts Institute of Technology [4] in this era. Tibshirani [1] is best known for co-developing Least angle regression [7], a computationally efficient method for model selection in high-dimensional settings that advanced regularization and interpretability crucial for the era. Trevor Hastie [2] has affiliations with the University of California, San Francisco [5] and Stanford University [6] during this era. Hastie [2] co-authored Least angle regression [7], a collaboration that helped advance high-dimensional estimation techniques central to causal-design and heterogeneous treatment effect analysis in this era.