Econometrics (Ofer Abarbanel online library)

Econometrics is the application of statistical methods to economic data in order to give empirical content to economic relationships.[1] More precisely, it is “the quantitative analysis of actual economic phenomena based on the concurrent development of theory and observation, related by appropriate methods of inference”.[2]

An introductory economics textbook describes econometrics as allowing economists “to sift through mountains of data to extract simple relationships”.[3] The first known use of the term “econometrics” (in cognate form) was by Polish economist Paweł Ciompa in 1910.[4] Jan Tinbergen is considered by many to be one of the founding fathers of econometrics.[5][6][7] Ragnar Frisch is credited with coining the term in the sense in which it is used today.[8]

A basic tool for econometrics is the multiple linear regression model.[9] Econometric theory uses statistical theory and mathematical statistics to evaluate and develop econometric methods.[10][11] Econometricians try to find estimators that have desirable statistical properties including unbiasedness, efficiency, and consistency. Applied econometrics uses theoretical econometrics and real-world data for assessing economic theories, developing econometric models, analysing economic history, and forecasting.

Basic models: linear regression

A basic tool for econometrics is the multiple linear regression model.[9] In modern econometrics, other statistical tools are frequently used, but linear regression is still the most frequently used starting point for an analysis.[9] Estimating a linear regression on two variables can be visualised as fitting a line through data points representing paired values of the independent and dependent variables.



Econometric theory uses statistical theory and mathematical statistics to evaluate and develop econometric methods.[10][11] Econometricians try to find estimators that have desirable statistical properties including unbiasedness, efficiency, and consistency. An estimator is unbiased if its expected value is the true value of the parameter; it is consistent if it converges to the true value as the sample size gets larger, and it is efficient if the estimator has lower standard error than other unbiased estimators for a given sample size. Ordinary least squares (OLS) is often used for estimation since it provides the BLUE or “best linear unbiased estimator” (where “best” means most efficient, unbiased estimator) given the Gauss-Markov assumptions. When these assumptions are violated or other statistical properties are desired, other estimation techniques such as maximum likelihood estimation, generalized method of moments, or generalized least squares are used. Estimators that incorporate prior beliefs are advocated by those who favour Bayesian statistics over traditional, classical or “frequentist” approaches.


Applied econometrics uses theoretical econometrics and real-world data for assessing economic theories, developing econometric models, analysing economic history, and forecasting.[12]

Econometrics may use standard statistical models to study economic questions, but most often they are with observational data, rather than in controlled experiments.[13] In this, the design of observational studies in econometrics is similar to the design of studies in other observational disciplines, such as astronomy, epidemiology, sociology and political science. Analysis of data from an observational study is guided by the study protocol, although exploratory data analysis may be useful for generating new hypotheses.[14] Economics often analyses systems of equations and inequalities, such as supply and demand hypothesized to be in equilibrium. Consequently, the field of econometrics has developed methods for identification and estimation of simultaneous equations models. These methods are analogous to methods used in other areas of science, such as the field of system identification in systems analysis and control theory. Such methods may allow researchers to estimate models and investigate their empirical consequences, without directly manipulating the system.

One of the fundamental statistical methods used by econometricians is regression analysis.[15] Regression methods are important in econometrics because economists typically cannot use controlled experiments. Econometricians often seek illuminating natural experiments in the absence of evidence from controlled experiments. Observational data may be subject to omitted-variable bias and a list of other problems that must be addressed using causal analysis of simultaneous-equation models.[16]

In addition to natural experiments, quasi-experimental methods have been used increasingly commonly by econometricians since the 1980s, in order to credibly identify causal effects.[17]


The main journals that publish work in econometrics are Econometrica, the Journal of EconometricsThe Review of Economics and StatisticsEconometric Theory, the Journal of Applied EconometricsEconometric ReviewsThe Econometrics Journal,[20] Applied Econometrics and International Development, and the Journal of Business & Economic Statistics.

Limitations and criticisms

Like other forms of statistical analysis, badly specified econometric models may show a spurious relationship where two variables are correlated but causally unrelated. In a study of the use of econometrics in major economics journals, McCloskey concluded that some economists report p-values (following the Fisherian tradition of tests of significance of point null-hypotheses) and neglect concerns of type II errors; some economists fail to report estimates of the size of effects (apart from statistical significance) and to discuss their economic importance. She also argues that some economists also fail to use economic reasoning for model selection, especially for deciding which variables to include in a regression.[21][22]

In some cases, economic variables cannot be experimentally manipulated as treatments randomly assigned to subjects.[23] In such cases, economists rely on observational studies, often using data sets with many strongly associated covariates, resulting in enormous numbers of models with similar explanatory ability but different covariates and regression estimates. Regarding the plurality of models compatible with observational data-sets, Edward Leamer urged that “professionals … properly withhold belief until an inference can be shown to be adequately insensitive to the choice of assumptions”.[23]


  1. ^ Hashem Pesaran (1987). “Econometrics,” The New Palgrave: A Dictionary of Economics, v. 2, p. 8 [pp. 8–22]. Reprinted in J. Eatwell et al., eds. (1990). Econometrics: The New Palgrave, p. 1 [pp. 1–34]. Abstract Archived 18 May 2012 at the Wayback Machine (2008 revision by J. Geweke, J. Horowitz, and H. P. Pesaran).
  2. ^ A. Samuelson, T. C. Koopmans, and J. R. N. Stone (1954). “Report of the Evaluative Committee for Econometrica,” Econometrica22(2), p. 142. [p p. 141-146], as described and cited in Pesaran (1987) above.
  3. ^Paul A. Samuelson and William D. Nordhaus, 2004. Economics. 18th ed., McGraw-Hill, p. 5.
  4. ^“Archived copy”. Archived from the original on 2 May 2014. Retrieved 1 May 2014.
  5. ^“1969 – Jan Tinbergen: Nobelprijs economie –”. 12 October 2015. Archived from the original on 1 May 2018. Retrieved 1 May2018.
  6. ^Magnus, Jan & Mary S. Morgan (1987) The ET Interview: Professor J. Tinbergen in: ‘Econometric Theory 3, 1987, 117–142.
  7. ^Willlekens, Frans (2008) International Migration in Europe: Data, Models and Estimates. New Jersey. John Wiley & Sons: 117.
  8. ^ H. P. Pesaran (1990), “Econometrics,” Econometrics: The New Palgrave, p. 2, citing Ragnar Frisch (1936), “A Note on the Term ‘Econometrics’,” Econometrica, 4(1), p. 95.
    • Aris Spanos (2008), “statistics and economics,” The New Palgrave Dictionary of Economics, 2nd Edition. Abstract.Archived 18 May 2012 at the Wayback Machine
  9. ^ Jump up to:ab c Greene, William (2012). “Chapter 1: Econometrics”. Econometric Analysis (7th ed.). Pearson Education. pp. 47–48. ISBN 9780273753568. Ultimately, all of these will require a common set of tools, including, for example, the multiple regression model, the use of moment conditions for estimation, instrumental variables (IV) and maximum likelihood estimation. With that in mind, the organization of this book is as follows: The first half of the text develops fundamental results that are common to all the applications. The concept of multiple regression and the linear regression model in particular constitutes the underlying platform of most modeling, even if the linear model itself is not ultimately used as the empirical specification.
  10. ^ Jump up to:ab Greene, William (2012). Econometric Analysis (7th ed.). Pearson Education. pp. 34, 41–42. ISBN 9780273753568.
  11. ^ Jump up to:ab Wooldridge, Jeffrey (2012). “Chapter 1: The Nature of Econometrics and Economic Data”. Introductory Econometrics: A Modern Approach (5th ed.). South-Western Cengage Learning. p. 2. ISBN 9781111531041.
  12. ^Clive Granger (2008). “forecasting,” The New Palgrave Dictionary of Economics, 2nd Edition. Abstract. Archived 18 May 2012 at the Wayback Machine
  13. ^Wooldridge, Jeffrey (2013). Introductory Econometrics, A modern approach. South-Western, Cengage learning. ISBN 978-1-111-53104-1.
  14. ^Herman O. Wold (1969). “Econometrics as Pioneering in Nonexperimental Model Building,” Econometrica, 37(3), pp. 369-381.
  15. ^For an overview of a linear implementation of this framework, see linear regression.
  16. ^Edward E. Leamer (2008). “specification problems in econometrics,” The New Palgrave Dictionary of Economics. Abstract. Archived 23 September 2015 at the Wayback Machine
  17. ^Angrist, Joshua D; Pischke, Jörn-Steffen (May 2010). “The Credibility Revolution in Empirical Economics: How Better Research Design is Taking the Con out of Econometrics”. Journal of Economic Perspectives. 24 (2): 3–30. doi:10.1257/jep.24.2.3. ISSN 0895-3309.
  18. ^Pearl, Judea (2000). Causality: Model, Reasoning, and Inference. Cambridge University Press. ISBN 978-0521773621.
  19. ^Card, David (1999). “The Causal Effect of Education on Earning”. In Ashenfelter, O.; Card, D. (eds.). Handbook of Labor Economics. Amsterdam: Elsevier. pp. 1801–1863. ISBN 978-0444822895.
  20. ^“The Econometrics Journal – Wiley Online Library”. Retrieved 8 October 2013.
  21. ^McCloskey (May 1985). “The Loss Function has been mislaid: the Rhetoric of Significance Tests”. American Economic Review. 75 (2).
  22. ^Stephen T. Ziliak and Deirdre N. McCloskey (2004). “Size Matters: The Standard Error of Regressions in the American Economic Review,” Journal of Socio-economics, 33(5), pp. 527-46 Archived 25 June 2010 at the Wayback Machine (press +).
  23. ^ Jump up to:ab Leamer, Edward (March 1983). “Let’s Take the Con out of Econometrics”. American Economic Review. 73 (1): 31–43. J

Ofer Abarbanel – Executive Profile

Ofer Abarbanel online library

Ofer Abarbanel online library

Ofer Abarbanel online library

Ofer Abarbanel online library