DEFINITION, NATURE AND SCOPE OF ECONOMETRICS

Econometrics means ‘Economic measurement’. The term ‘Econometrics’ is

formed from two Greek words ’OIKONOMIA’ (Economy) and ‘Metpov’
(measure). Thus econometrics can be defined as that branch of economics
concerned with the empirical estimation of economic relationships. Econometrics
can be considered as the integration of Economics, Mathematics and Statistics for
the purpose of providing numerical values for the parameters of economic
relationships and verifying economic theories.

In the words of Ragner Frisch in 1933 (Econometrica vol.1. No.1) gave a

clear idea of the scope and method of econometrics: “…………. Experience has
shown that each of these view points, that of Statistics, Economic theory and
Mathematics, is a necessary, but not by itself sufficient, condition for a real
understanding of the quantitative relations in modern economic life. It is the
unification of all the three that constitutes Econometrics”.

Thus econometrics may be considered as the integration of Economics,

Mathematics and Statistics for the purpose of providing numerical values for the
parameters of economic relationships. (eg:- Elasticities, Propensities, Marginal
Values) and verifying economic theories. The main object shall be to promote
studies that aim at a unification of the theoretical ad empirical approaches to
economic problems that originate by constructive and rigorous thinking applicable
to natural sciences.

DEFINITIONS:

The term ECONOMETRICS was coined by Ragner Frisch in 1926. Econometrics

could be defined as statistical observations of theoretically founded concepts or
alternatively mathematical economics working with measured data. In short:
ECONOMICS + MATHEMATICS = MATHEMATICAL ECONOMICS

and MATHEMATICAL ECONOMICS + STATISTICS = ECONOMETRICS.

P.A.Samuelson:- “………. Econometrics may be defined as the quantitative

analysis of actual economic phenomena based on the concurrent development of
theory and observation, related by appropriate methods of inference” (1954).

Gernard Tintner:- “ Econometrics, the result of a certain outlook on the role of

economics, consists of the application of mathematical statistics to economic data
to lend empirical support to the models constructed by mathematical economic and
to obtain numerical results”(1968).

Arthur. S. Goldberger:- “Econometrics may be defined as the social science in

which the tools of economic theory, mathematics and statistical inference are
applied to the analysis of economic phenomena” (1964).

Theil H:- “Econometrics is concerned with the empirical determination of

economic laws” (1971).

T Haavelmo:- “ The method of Econometric research aims, essentially, at a

conjunction of economic theory and actual measurements, using the theory and
technique of statistical inference as the bridge pier” (1944).

NATURE OF ECONOMETRICS:

Econometrics is mainly interested in the empirical verification of economic

theory. The prime difference is that, economic theory makes statements or
hypothesis that are mostly qualitative in nature (eg;- Demand – Price relationship
postulates a negative or inverse relation between price and quantity demanded for a
commodity). The theory does not provide any numerical measure of this
relationship between the two variables. Here, econometrics provide numerical
estimates and gives empirical content to economic theory. Econometrics uses
mathematic equations and does empirical testing. Using statistical data and
analytical treatment of these data gives accurate estimation of parameters and
empirical results.

Econometrics concerns itself with estimation and testing of Economic

relationships which are of three types:

1. Behavioral Relationship : which are derived from theories which postulate

certain kinds of behavior on the part of certain agents. Eg:- Consumers
maximize utility. i.e.,
[𝑈 = 𝑓 (𝑞1 , 𝑞2 )] Consumption function, Demand function etc.
2. Technological Relationship : which reflect the underlying technologies,
Eg:- [Q = f (L,K) Production function].
3. Accounting Identities : such as those in National Income accounts or
Financial accounting. Eg:- [Y = C+I or Y = C+S].

These relationships are generally cast in the form of algebraic equations or

inequalities which contains:
1. Variables [i.e, entities or constructs whose behavior is relevant to the
phenomena under analysis and are observed and measured] and
2. Parameters [i.e, fixed, unknown constants which link up the variables into a
relationship]
Equations of the above three types are called Autonomous Equations. A collection
of exact or deterministic autonomous equations with specified numerical values for
the parameters is called a structure and equations contained in the structure are
called Structural Equations.
Note: Variables are of two types:
a) Exogeneous Variables (Independant)
b) Endogeneous Variables (Dependant)
Dependant Variable Independent Variable
Endogenous Exogenous
Explained Variable Explanatory Variable
Regressand Regressor
Predictand Predictor
Response Stimulus
Outcome Covariate
Controlled Variable Control Variable

ROLE OF ECONOMETRICS:

The primary role of econometrics is the estimation and testing of economic

models. Steps involved in the process:

1. Specification of the Model.

2. Appropriate data to be assembled.
3. Estimation of Parameters.
4. Statistical Inference.
5. Forecasting.

ECONOMETRIC MODELLING:

Starting from the relationship of economic theory, we expressed them in

mathematical terms, which are generally called ‘Model Building’, so that they can
be measured by using a specific method called Econometrics.
Broadly, econometrics can be classified into;-

1. THEORETICAL ECONOMETRICS.
2. EMPIRICAL ECONOMETRICS.

Theoretical econometrics is done by fairly abstract or general basis. Empirical

econometrics deals with actual data and sets out to make numerical statements of
economic relationships.

Let us discuss briefly, how, econometricians face an economic problem;

Mathematical economics puts the literal form of economics in terms of
mathematical symbols. Economic theory and Mathematical economics does not
take into account , uncertainty of subjective variables which play a role on
conditioning human behavior. The relations in economic theory and mathematical
economics are non-stochastic in nature. But, most important characterization of
econometric relation is that they contain a random element, which however is
ignored by economic theory and mathematical economics. At the same time,
econometricians have developed the methods for dealing with the random
component of economic relationships. Econometricians also face the problem of
errors of observations of actual data. Therefore, econometricians assume every
economic relation as a stochastic one.

Generally, an econometric model has two forms:

a) A DETERMINISTIC MODEL: A collection of autonomous equations is

defined as a deterministic model. It specifies the variables being dealt with
the functional form of the relationships.
b) A STOCHASTIC MODEL: A stochastic model contains a deterministic
model as the systematic part and, in addition, specifies how random
 disturbances enter and how they are generated i.e, their probability
distributions.

Illustration with an example:

Economic theory postulates that demand for a commodity depends on its own
price, prices of other commodities, consumers’ income and on tastes and
preferences. This is an exact relationship, because, demand is completely
determined by the above factors. In mathematical economics, we express the
abstract economic relationship in mathematical form:

𝑄𝑑 = 𝛽0 + 𝛽1 𝑃 + 𝛽2 𝑃𝑂 + 𝛽3 𝑌 + 𝛽4 𝑇 ………………….. (1)

This is a deterministic model.

Where, 𝑄𝑑 → Quantity demanded, P → price of the commodity. 𝑃𝑂 → price of

related commodities 𝑌 → Consumers’ income T → appropriate measure of taste.

𝛽0 , 𝛽1 , 𝛽2 , 𝛽3 , 𝛽4 → Coefficients (parameters) of the demand equation.

𝑄𝑑 , 𝑃, 𝑃𝑂 , 𝑌, 𝑇 → are variables.

𝑄𝑑 → endogenous variable. 𝑃, 𝑃𝑂 , 𝑌, 𝑇 → exogenous variables.

The above demand equation indicates that quantity demanded will change only if
some of the factors appearing on the RHS of the equation changes. But, in practical
experience, demand is also influenced by various social, political and subjective
factors. In econometrics, the influence of other factors is taken into account by the
introduction of a random variable (error term) into the economic relationship eqn
(1) with special characteristics. Therefore, the demand function can be rewritten
into a stochastic form as,
𝑄𝑑 = 𝛽0 + 𝛽1 𝑃 + 𝛽2 𝑃𝑂 + 𝛽3 𝑌 + 𝛽4 𝑇 + 𝑈𝑖 …………………. (2)

Where, 𝑈𝑖 is the random variable (error term).

There also exists pre – determined variables, i.e, Lagged Endogenous variables
that supports the exogenous variables as shown in the following model:

𝑌𝑡 = 𝐶𝑡 + 𝐼𝑡 + 𝐺𝑡 …………………….. (3) → Identity.

𝐶𝑡 = 𝛼0 + 𝛼1 ( 𝑌𝑡 − 𝑇𝑡 ) …………………….. (4) → Behavioral eqn.

𝐼𝑡 = 𝛽1 𝑌𝑡−1 + 𝛽2 𝑅𝑡 ……………………….(5) → Behavioral eqn.

Where, the ‘a priori’ restrictions on the model are expressed by

0 < 𝛼1 < 1 , 𝛽1 > 0, 𝛽2 < 0.

Here, C → Consumption, I → investment, Y → National Income, G → Government

expenditure on goods and services, T → Taxes on income and R → the
Government regulator.

The model constitutes two behavioral equations (eqns 4 and 5) and one identity
(eqn 3). The model formulated refers to discrete time periods and specified a one –
period lag for National Income in the Investment function.

The classification of variables are as follows:

𝐶𝑡 , 𝐼𝑡 𝑎𝑛𝑑 𝑌𝑡 → Current endogenous variables.

𝑇𝑡 , 𝑅𝑡 𝑎𝑛𝑑 𝐺𝑡 → Current exogenous variables.

𝑌𝑡−1 → Lagged endogenous variable.

The rationale of this model classification purports to explain the values of
endogenous variables in the current period (t) w.r.t. the values taken by the
exogenous and lagged endogenous variables. Thus,

Relations (3) to (5) are described as the Structural form. These equations can be
changed into its Reduced form as:

Sub eqn (3) and (5) into eqn (4)

𝐶𝑡 = 𝛼0 + 𝛼1 ( 𝐶𝑡 + 𝛽1 𝑌𝑡−1 + 𝛽2 𝑅𝑡 + 𝐺𝑡 − 𝑇𝑡 ) …………….. (6a)

𝛼0 𝛼1 𝛽1 𝛼1 𝛽2 𝛼1
𝐶𝑡 = + 𝑌𝑡−1 + 𝑅𝑡 + (𝐺𝑡 − 𝑇𝑡 ) ……………. (6b)
1− 𝛼1 1− 𝛼1 1− 𝛼1 1− 𝛼1

Thus, the primary ingredients of the econometric model are:

a) A clearly specified model.

b) Data, i.e, observations on the values of the variables in the model.
c) Statistical techniques of estimation and inference.

DIVISION OF ECONOMETRICS:

ECONOMETRICS

METHODS: APPLICATIONS

1. SINGLE EQUATION:
a) CLASSICAL LEAST SQUARES.
a) GENERALIZED LEAST SQUARES.
 ESTIMATION
 TESTING
 FORECASTING
 DUMMY VARIABLES
a) SEASONAL ADJUSTMENT
b) COVARIANCE ANALYSIS
 LINEAR REGRESSION
 GROUPING OF VARIABLES
 SPECIFICATION ERROR
 MULTICOLLINEARITY
 LAGGED VARIABLES
 ERRORS IN VARIABLES
 A PRIORI INFORMATION
 AUTO CORRELATION
 HETEROSCEDASTICITY
2. SIMULTANEOUS EQUATION:
a) IDENTIFICATION
b) ESTIMATION
 TWO STAGE LEAST SQUARES
 LIMITED INFORMATION
 THREE STAGE LEAST SQUARES
 FULL INFORMATION MAXIMUM LIKELIHOOD

1. MODELS OF THE NATIONAL ECONOMY:

 AGGREGATIVE
 LESS AGGREGATIVE
  HIGHLY AGGREGATIVE
2. MODELS OF SECTORS:
 CONSUMER BEHAVIOR
 FIRMS AND INDUSTRIES
 FOREIGN TRADE
 Etc.

DESIRABLE PROPERTIES OF AN ECONOMETRIC MODEL:

An econometric model is a model whose parameters have been estimated with

some appropriate econometric technique.

The GOODNESS of an econometric model is judged customarily according to the

following desirable properties:

1. Theoretical Plausibility: The model should be compatible with the postulates

of economic theory. I t must describe adequately the economic phenomena
to which it relates.
2. Explanatory Ability: The model should be able to explain the observations
of the actual world. I t must be consistent with the observed behavior of the
economic variables whose relationship it determines.
3. Accuracy of the estimates of the parameters: The estimates of the
coefficients should be accurate in the sense that they should approximate as
best as possible the true parameters of the structural model. The estimates
should if possible possess the desirable properties of a good estimator.
4. Forecasting Ability; The model should produce satisfactory predictions of
future values of the endogenous variables.
5. Simplicity: The model should represent the economic relationships with
maximum simplicity. The fewer the equations and the simpler their
 mathematical form, the better the model is considered. ‘ceteris paribus’ (i.e,
to say provided that the other desirable properties are not affected by the
simplifications of the model).

METHODOLOGY OF ECONOMETRICS:

Econometrics is concerned with the measurement of economic variables. Starting

from the relationships of economic theory, economic research generally proceed
along the following lines:

1. SPECIFICATION: Specification of mathematical equations to describe the

relationship between economic variables as proposed by economic theory.
2. COLLECTION OF DATA: Mathematical designs , methods and procedures
based on statistical theory, to obtain representative samples of the real world.
3. ESTIMATION: Development of methods of estimating the parameters of
the specified relationships described in estimation.
4. VERIFICATION: Development of statistical method to test the validity of
theory by using estimated parameters.
5. APPLICATION: Development of methods for economic forecasts or policy
implications based on the estimated parameters.

There are five steps in this process showing the requirements and possible errors;

Stage I: SPECIFICATION:

Requirements: Specifying relationships based on economic theories or maintained

hypothesis.

Possible errors: Exclusion of relevant variables, Inclusion of irrelevant variable,

Specification bias and under identification.
Stage II: STATISTICAL DESIGNS TO OBTAIN DATA:

Data: Time Series, Cross section and Panel Data.

Stage III: ESTIMATION AND EVALUATION OF THE COEFFICIENTS:

To test the reliability, there are three criteria:

 Economic ‘A Priori Criteria.

 Statistical Criteria.
 Econometric Criteria.

Requirements: Estimators possess the following properties:

1. Linearity
2. Unbiasedness
3. Minimum Variance
4. Consistency
5. Efficiency
6. Sufficiency

Possible errors: Auto correlation, Heteroscedasticity and Multicollinearity.

Stage IV: VERIFICATION:

Requirements: Economic interpretation of the results obtained in stage iii.

Evaluation of economic theory or hypothesis.

Possible errors: Wrong and irrelevant tests evolved to verify the validity of the
hypothesis.

Stage V: FORECASTING:

Requirements: The ultimate goal of econometrics is to obtain predictions.

Possible errors: Biased forecasts; when forecasts are used for policy purposes they
lead to losses in welfare of the society.

…………………………………