(redirected from econometric)
Also found in: Dictionary, Thesaurus, Financial, Wikipedia.
Related to econometric: Econometric analysis


econometrics, technique of economic analysis that expresses economic theory in terms of mathematical relationships and then tests it empirically through statistical research. Econometrics attempts to develop accurate economic forecasting and to make possible successful policy planning. The term econometrics is generally attributed to Norwegian economist Ragnar Frisch, who wrote important studies on the subject in the mid-20th cent. and founded the Econometric Society. In the 1930s econometrics emerged as an important method of economic study on a national level, as part of a broad, new field called macroeconomics. In the 1950s economists such as Lawrence Klein applied Keynesian principles to econometrics and formed macroeconometric models of the economy of the United States. Scholars, economists, and public officials soon followed Klein's lead and began to use large-scale econometric models in both historical and planning analyses.

With changes in the 1970s from fixed to floating exchange rates and inflation heavily influencing the economy, criticism of econometircs grew considerably. The accuracy of econometric models was also questioned given their failure to predict, for example, the Asian financial failures in 1997–98. In the late 1990s econometrics began to be used in advertising (where it is also called “market-mix modeling”), in which the models measure and predict sales performance. Econometrics has been significantly aided by advances in computer technology.


See R. J. Epstein, A History of Econometrics (1986); D. N. Gujarti, Basic Econometrics (3d ed. 1995); P. Kennedy, Guide to Econometrics (4th ed. 1998); and J. J. Heckman and E. E. Learner, Handbook of Econometrics (1999).

The Columbia Electronic Encyclopedia™ Copyright © 2022, Columbia University Press. Licensed from Columbia University Press. All rights reserved.


quantitative economic analysis which combines economic theory with statistical analysis. Econometrics is employed in theoretical modelling, policy analysis and forecasting, as well as in historical analysis.
Collins Dictionary of Sociology, 3rd ed. © HarperCollins Publishers 2000
The following article is from The Great Soviet Encyclopedia (1979). It might be outdated or ideologically biased.



the study of the specific quantitative regularities and interrelationships of economic objects and processes by means of mathematical and statistical techniques and models. The models used in econometrics yield numerical results on the basis of statistical, forecasting, and planning data. Econometrics is sometimes broadly construed as the modeling of economic processes in general, including abstract theoretical models.

The potential uses of econometrics depend on the degree to which a model reflects the objective laws discovered by economics, on the availability and quality of the data, and on the techniques employed in their evaluation and processing. In some instances, on the other hand, econometrics makes it possible to use factual material in order to concretize and verify theoretical hypotheses and models in the economic sciences.

K. Marx noted the possibility of “mathematically deducing . . . the main laws of crises” from the analysis of such factors as price dynamics and discount rates (K. Marx and F. Engels, Soch., 2nd ed., vol. 33, p. 72). Some early attempts at the mathematical formalization of economic and statistical data were made in the 19th and early 20th centuries—for example, V. Pareto’s derivation of the hyperbola equation to describe income distribution in the capitalist countries (1897), the works of R. Hooker (Great Britain) on correlation analysis in economics, and the works of the Russian statistician A. A. Chuprov. But it was not until the 1920’s and 1930’s that econometrics—owing particularly to the works of H. Moore and H. Schultz (USA)—emerged as an independent scientific school that combined economic theory, statistics, and mathematics. The term “econometrics” was introduced by the Polish economist P. Czompa (1910); it was adopted as a scientific term by the Norwegian economist R. Frisch (1926), who was a founder of the International Econometric Society (1930) together with the Americans I. Fisher and C. Roos.

It was within the framework of econometrics that analytical-statistical models were first developed to express the correlation between an economic process and other factors presumed to influence it. An early example of such a model was the “economic barometer,” which was based on the empirically observed tendency of some business indicators to lag behind others. The model that was best known—the “Harvard barometer,” which W. Mitchell helped design—proved incapable of predicting the major economic crisis of 1929–33. The failure of purely empirical constructions led to increased interest in the theoretical validation of econometric models; in bourgeois economics, such validation was based on the subjectivist theory of marginal utility, the general theory of equilibrium of the market, and the works of J. M. Keynes.

Analytical-statistical econometric models are usually represented by regression equations, whose parameters are obtained from statistical processing of the data; in most instances the relationship between variables (or their logarithms) is assumed to be linear. Such equations serve to express various functions, including demand (that is, its dependence on such factors as prices, volume of output, income, and taxes), supply, costs, imports, and exports. This category also includes production functions that reflect the technological dependence of output on the expenditure of labor and means of production. The first and simplest production function was formulated by C. Cobb and P. Douglas (USA, 1928); it was subsequently generalized by R. Solow and K. Arrow (USA), who took into account the influence of various factors—for example, scale of production and technological advances. Such regression models can be constructed for individual products, enterprises, firms, and branches, or for the national economy as a whole.

A number of multiple-factor correlation models were developed by J. Tinbergen (Netherlands) m the 1930’s and by L. Klein (USA) and R. Stone (Great Britain) in the 1950’s. These models describe the statistical interrelation of many variables—including production, ultimate private and state demand, prices, taxes, foreign trade, depreciation and accumulation of capital, and supply of labor power—in the economies of various capitalist countries. Such models include aggregates of hundreds of equations and identities, which increases the difficulties involved in the statistical identification of the objects under study and in the evaluation of the models’ parameters.

An example of the type of model that is used to analyze the structure of the national economy is the intersector balance model, which serves to reveal intersector and interregional relations and cost components, as well as the distribution of gross output and final product. The first intersector balance of the national economy was compiled in the USSR under the supervision of P. I. Popov (1925–26). This method was subsequently developed by W. Leontief (USA). R. Frisch was among those who used this method to analyze the flow of money, thus leading to the establishment of the national accounts system adopted by the UN.

In the analysis of economic dynamics, economic growth models are used in order to examine the relationship between consumption and accumulation, with due regard to the influence of various economic factors on this process. An early model of this type, based on Marx’ proposed plan of reproduction, was developed by the Soviet economist G. A. Fel’dman (1928). Various models of economic dynamics, especially geared to the analysis of the capitalist cycle, were developed abroad—for example, by Tinbergen, Frisch, M. Kalecki, J. Hicks, R. Harrod, and P. Samuelson.

Econometric methods are based on the extrapolation of trends as revealed by the statistical processing of time series. Inasmuch as extending the forecasting range of economic dynamics reduces the reliability of such methods, it is necessary to resort to expert evaluations of the changes in certain factors that are specifically associated with scientific and technological progress and sociopolitical conditions.

While the various types of models—that is, correlation, balance, and dynamic models—were developed independently of one another, today’s aggregate econometric models bring together different types of analytical models in reciprocal association. Such aggregate models are extensively used for economic forecasts and for analyzing alternative economic policies; in the socialist countries they are used for alternative calculations in national economic planning. These issues are discussed in the works of V. S. Nemchinov, B. N. Mikhalevskii, A. G. Aganbegian, A. N. Efimov, E. F. Baranov, L. Ia. Berri, E. B. Ershov, F. N. Klotsvog, V. V. Kossov, L. E. Mints, S. S. Shatalin, and M. R. Eidel’man of the USSR, O. Lange of Poland, and J. Kornai of Hungary.

Many specialists define the task of econometrics as the formalized description and forecasting of economic processes based on the statistical analysis of data; they restrict econometrics to the development and application of analytical models, and sometimes they use only the traditional analytical-statistical, or regression, models. In the 1930’s, however, another class of models emerged—namely, the normative models. These models make it possible not only to evaluate the varying structure and dynamics of economic objects but also to select the optimal alternative according to a given criterion of evaluation.

A significant contribution to the development of normative models was made by the Soviet scientist L. V. Kantorovich, who devised linear programming (1939); this enabled him, together with others—such as V. V. Novozhilov and A. L. Lur’e of the USSR and T. Koopmans and G. Dantzig of the USA—to formulate and resolve a broad spectrum of economic problems related to the optimal distribution and utilization of resources. The refinement of optimization methods led to new types of normative models; the works of J. Von Neumann had a major impact in this area.

Types of models vary with the nature of the variables and the form of relationship between them; for example, models may be linear or nonlinear, continuous or discrete, predetermined or stochastic. Depending on the models’ specific features, appropriate methods of mathematical programming, operations research, and game theory are applied in each case. In the socialist countries, normative models are widely used in the optimization of national economic planning at all levels (as exemplified by the works of N. N. Nekrasov and N. P. Fedorenko on chemicalization and on the development of the chemical industry in the USSR). In the capitalist countries, optimization methods are applied by individual firms and are also used in the development of state programs. The USSR and other socialist countries are engaged in wide-ranging studies of the internal relationship between normative and analytical models and are developing aggregate models that incorporate both the normative and the analytical type.

Econometric reseat eh and development in the USSR are the concern of the Central Economic Mathematical Institute, the Institute of Economics and Management of Industrial Production, and the Institute of World Economics and International Relations of the Academy of Sciences of the USSR, as well as by the institutes of the State Planning Committee of the USSR and of other Union republics, and many branch institutes and higher educational institutions. Works on econometrics have been regularly published since 1965 in the journal Ekonomika i matema-ticheskie melody. The best-known journal abroad is Econometrica (since 1933).


Kantorovich, L. V. Ekonomicheskii raschet nailuchshego ispol’zovaniia resursov. Moscow, 1959.
Lange, O. Vvedenie v ekonometriku. Moscow, 1964. (Translated from Polish.)
Tintner, G. Vvedenie v ekonometriiu. Moscow, 1965. (Translated from German.)
Nemchinov, V. S. hbr. proizvedeniia, vol. 3. Moscow, 1967.
Tinbergen, J., and H. Bos. Matematicheskie modeli ekonomicheskogo rosta. Moscow, 1967. (Translated from English.)
Nauchnye osnovy ekonomicheskogo prognoza. Moscow, 1971.
Kossov, V. V. Mezhotraslevye modeli. Moscow, 1973.
Modelirovanie narodnokhoziaistvennykh protsessov. Moscow, 1973.
Kobrinskii, N. E., E. Z. Maiminas, and A. D. Smirnov. Vvedenie v ekonomicheskuiu kibernetiku. Moscow, 1975.
Malinvaud, E. Statisticheskie metody ekonometrii, vols. 1–2. Moscow, 1975–76.


The Great Soviet Encyclopedia, 3rd Edition (1970-1979). © 2010 The Gale Group, Inc. All rights reserved.


(industrial engineering)
The application of mathematical and statistical techniques to the estimation of mathematical relationships for testing of economic theories and the solution of economic problems.
McGraw-Hill Dictionary of Scientific & Technical Terms, 6E, Copyright © 2003 by The McGraw-Hill Companies, Inc.
References in periodicals archive ?
However, the dollar has significant explanatory power if the Fed Funds Rate is excluded from our econometric model.
In that context, econometrics becomes a very important aspect of research in economics.
For example, subgroups were not combined when they addressed different forest product types or econometric models.
It was against this backdrop that Lucas (1976) published his famous paper 'Econometric Policy Evaluation: a Critique'.
Three approaches, namely, growth accounting approach, index number approach, and econometric approach are commonly used to measure TFP growth.
While the book is quite academic, interspersed with econometric terms in some chapters, it is written with great clarity and sound economic explanation.
We classify each paper into one and only one of the following research fields: applied, applied theory, econometric methods, and theory.
The first chapter of the book deals with randomized trials (RT), a topic virtually nonexistent in standard econometric courses.
New Directions in Econometric Practice, General to Specific Modelling, Cointegration and Vector Auto Regression.
The employed methodology is a compound of econometric structural modeling combined with time series approach of ARMA.
He has developed several econometric models to predict commercial real estate market trends, has authored numerous studies and survey reports and regularly provides media commentary on the commercial real estate market and related business trends.