ECONOMETRICS

'Econometrics' is concerned with the tasks of developing and applying quantitative or statistical methods to the study and elucidation of economic principles.^[1] Econometrics combines economic theory with statistics to analyze and test economic relationships. Theoretical econometrics considers questions about the statistical properties of estimators and tests, while applied econometrics is concerned with the application of econometric methods to assess economic theories.

Contents

Purpose

Methods

Example

Notable Econometricians

Journals

Notes

References

See also

Software

General packages

Time series packages

Cross-section packages

Other statistical package links

Purpose

The two main purposes of econometrics are to give empirical content to economic theory and to subject economic theory to potentially falsifying tests.^[2]
For example, consider one of the basic relationships in economics, the relationship between the price of a commodity and the quantity of that commodity that people wish to purchase (the demand relationship). Another way to view this complication is to note that
the parameters and are not
regression coefficient but, rather, causal (or counterfactual)
coefficients.Pearl, J. ''Causality: Models, Reasoning, and Inference,'' Cambridge University Press, 2000. In other words,
stands for the change in $Q$ due to a unit
increase in Price, when all other variables in the system
are held constant by external means. Such external means
are rarely available in economic studies.
According to economic theory, an increase in the price should lead to a decrease in the quantity demanded. Using econometric tools, a researcher would write a mathematical equation that described the relationship between price and quantity (which may include other variables like income):
:
Naive econometric methods would use regression analysis to estimate the unknown parameters , , and in the relationship, using data on price, income, and quantity demanded. The researcher would then statistically test that an increase in price leads to a decrease in the quantity demanded by testing the hypothesis that
.
Even in this example, however, the complications of econometrics become apparent. In order to estimate the demand relationship, the observations in the data set must be price and quantity pairs that are collected along a demand equation that is stable or unshifting. Since we can't guarantee that this is true in any given data set, simultaneous equations methods must be employed to estimate a demand relationship.

Methods

One of the fundamental statistical methods used by econometricians is regression analysis. For an overview of a linear implementation of this framework, see linear regression. 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.^[3]
Data sets to which econometric analyses are applied can be classified as time-series data sets, cross-sectional data sets, panel data sets, and multidimensional panel data sets. Time-series data sets contain observations over time; for example, inflation over the course of several years. Cross-sectional data sets contain observations at a single point in time; for example, many individuals' incomes in a given year. Panel data sets contain both time-series and cross-sectional observations. Multi-dimensional panel data sets contain observations across time, cross-sectionally, and across some third dimension. For example, the Survey of Professional Forecasters contains forecasts for many forecasters (cross-sectional observations), at many points in time (time series observations), and at multiple forecast horizons (a third dimension).
Econometric analysis may also be classified on the basis of the number of relationships modelled. Single equation methods model a single variable (the dependent variable) as a function of one or more explanatory (or independent) variables. In many econometric contexts, such single equation methods may not recover the effect desired, or may produce estimates with poor statistical properties. Simultaneous equation methods have been developed as one means of addressing these problems. Many of these methods use variants of instrumental variable to make estimates.
Other important methods include Method of Moments, Generalized Method of Moments (GMM), Bayesian methods, Two Stage Least Squares (2SLS), and Three Stage Least Squares (3SLS).

Example

A simple example of a relationship in econometrics from the field of labor economics is
:.
Economic theory says that the natural logarithm of a person's wage is a linear function of the number of years of education that person has acquired. The parameter measures the increase in the natural log of the wage attributable to one more year of education. The term $epsilon$ is a random variable representing all other factors that may have direct influence on wage. The econometric goal is to estimate the parameters, under specific assumptions about the random variable $epsilon$. For example, if $epsilon$ and Years of Education are uncorrelated, then the equation can be estimated with ordinary least squares.
If the researcher could randomly assign people to different levels of education, the data set thus generated would allow the econometrician to estimate the effect of changes in years of education on wages. In reality, those experiments cannot be conducted. Instead, the econometrician observes the years of education of and the wages paid to people who differ along many dimensions. Given this kind of data, the estimated coefficient on Years of Education in the equation above reflects both the effect of education on wages and the effect of other variables on wages, if those other variables were correlated with education. For example, people with more innate ability may have higher wages and higher levels of education. Unless the econometrician controls for innate ability in the above equation, the effect of innate ability on wages may be falsely attributed to the effect of education on wages.
The most obvious way to control for innate ability is to include a measure of ability in the equation above. Exclusion of innate ability, together with the assumption that $epsilon$ is uncorrelated with education produces a misspecified model. A second technique for dealing with omitted variables is instrumental variables estimation.

Notable Econometricians

Nobel Memorial Prize in Economics recipients in the field of econometrics:

★ Jan Tinbergen and Ragnar Frisch were awarded (in 1969) the first Nobel Prize for Economic Sciences for having developed and applied dynamic models for the analysis of economic processes.

★ Lawrence Klein, Professor of Economics at the University of Pennsylvania, was awarded in 1980 for his computer modeling work in the field.

★ Trygve Haavelmo was awarded in 1989. His main contribution to econometrics was his 1944 article (published in ''Econometrica'') "The Probability Approach to Econometrics."

★ Daniel McFadden and James Heckman shared the award in 2000 for their work in microeconometrics. McFadden founded the econometrics lab at the University of California, Berkeley.

★ Robert Engle and Clive Granger were awarded in 2003 for work on analysing economic time series. Engle pioneered the method of autoregressive conditional heteroskedasticity (ARCH) and Granger the method of cointegration.
The Econometric Author Links of the Econometrics Journal provides personal links to recent articles and working papers of econometric authors via the RePEc system in EconPapers.

Journals

The main journals which publish work in econometrics are Econometrica, The Journal of Econometrics, the Review of Economics and Statistics, and The Journal of Applied Econometrics.

Notes

1. Ragnar Frisch
(1933). "Editor's Note". ''Econometrica'' '1'. 1-4.
2.
★ M. Pesaren Hashem. "Econometrics,"'', v. 1 (1987), pp. 8-22.
3. Edward E. Leamer, "specification problems in econometrics," '', v. 4 (1987), pp. 472-75.

References

★ ''Handbook of Econometrics'' Elsevier, links to:
:v. 1, pp. 3-771 (1983)
:v. 2, pp. 775-1461 (1984)
:v. 4, pp. 2111-3155 (1994)
:v. 3, pp. 1465-2107 (1986)
:v. 5, pp. 3159-3843 (2001)

★ Harry H. Kelejian and Wallace E. Oates (1989, 3rd ed. troduction to Econometrics''.

★ Peter Kennedy (2003). ''A Guide to Econometrics'', 5th ed.

★ Robert S. Pindyck and Daniel L. Rubinfeld (1998, 4th ed.).

★ A.H. Studenmund (2000, 4th ed.) ''Using Econometrics: A Practical Guide''.

See also

★ Correlation does not imply causation

★ Modeling and analysis of financial markets

★ Important publications in econometrics

★ Wooldridge, Jeffrey. ''Introductory Econometrics: A Modern Approach.'' Mason: Thomson South-Western, 2003. ISBN 0-324-11364-1

★ Hayashi, Fumio. ''Econometrics.'' Princeton University Press, 2000.

★ Econometric Links

★ Single equation methods (econometrics)

★ Granger causality

★ Augmented Dickey-Fuller test

★ Unit root

★ Applied Econometric Association

★ Pearl, J. ''Causality: Models, Reasoning and Inference'', Cambridge University Press, 2000.

★ "The Art and Science of Cause and Effect": a slide show and tutorial lecture by Judea Pearl

Software

Software packages that are widely used by econometricians can be roughly categorized as follows:

General packages

★ R programming language

★ Matlab

★ Gauss

★ SAS

Time series packages

These are packages that are mainly used for time series analysis, although many include commands for other types of analysis as well.

★ RATS

★ EViews

★ gretl

★ PcGive

Cross-section packages

These are packages that are mainly used for cross-section data.

★ Stata

★ SPSS

Other statistical package links

★ List of statistical packages

★ Comparison of statistical packages

★