University of Gondar
School of economics
Econometrics for Management
Chapter one: introduction to
econometrics
1.1. Definition and Scope of Econometrics
So, what is econometrics?
Literally speaking “Econo” is related to economic aspects and
“metrics” is related to measurement. Combined together,
econometrics implies “activities related to economic
measurement”.
Econometrics is based upon the development of statistical
methods for estimating economic relationships, testing economic
theories, and evaluating and implementing government and
business policy.
The most common application of econometrics is the forecasting
of such important macroeconomic variables as interest rates,
1.1. Definition and Scope of Econometrics
Why a separate discipline?
Mathematical economics is used to express economic theory in
mathematical form, equation or symbol without regard to
measurability or empirical verification of the theory. It assumes
relationships in an exact or deterministic form.
Econometrics, on the other hand, does not assume exact or
deterministic relationship rather it assumes random or stochastic
relationships among economic variables. Moreover, it is interested
in the empirical verification of economic theory.
1.1. Definition and Scope of Econometrics
For this reason, statistical methods of measurement are not
appropriate for a number of economic relationships because for
most economic relationships controlled or carefully planned
experiments cannot be designed due to the fact that the nature of
relationships among economic variables are stochastic or random.
These all necessitate the study of econometrics as a separate
discipline.
For that matter, econometrics uses a combination of economic
theory, mathematical, and statistical methods for the purpose of
providing numerical values for the parameters of economic
relationships, and verifying them or refuting them.
1.2. Economic models and Econometric models
Economic model:
It is a set of assumptions that approximately describes the behavior
of an economy (or a sector of an economy), the relationships that
describes the functioning of an economic entity. Since it is not
possible to account for all the economic variables affecting a
certain other variable, we model it using selected variables which
are deemed important.
Economic models consist of the following three basic structural
elements.
A set of variables
A list of fundamental relationships and
1.2. Economic models and Econometric models
Econometric model:
An econometric model consists of the following. A set of
equations derived from economic model. These equations involve
some observed variables and some “disturbances” which accounts
for unforeseen events. We will discuss these concepts in the
subsequent sections.
Consider, for example, an economic model for the demand
equation from
This simple model assumes that demand (𝑄𝑑) is determined by
price (p).
1.2. Economic models and Econometric models
This is called an economic model, simply showing the relationship
between price and quantity only, and ignoring the possible effect
of any other economic variable. This is what we call deterministic
or exact relationship. However, price is not the only factor
affecting demand for a commodity. For example, income of the
consumer, his/her expectation, and other variables that affect
demand are excluded from the model. Hence, we need another
variable which accounts the effects of all omitted variables. This is
commonly represented by 𝑢𝑖 . This 𝑢𝑖 is called stochastic variable
or random component, error term, or disturbance term.
1.3. Methodology of Econometrics
1. Statement of Theory or Hypothesis
This is made in accordance with the intuition of economic theory or
earlier empirical works. In this step we distinguish the:
dependent and independent variables
Example: the theory from introductory macroeconomics postulates that
consumption depends on income level. Here, consumption is the
dependent variable and income is the independent variable.
a priori theoretical expectations about the magnitude and sign of the
parameters.
For example, we expect that marginal propensity to consume is between
zero and one. then, proceed to the second stage which is mathematical
form of the model
1.3. Methodology of Econometrics
2. Specification of the Mathematical Model
This is also based on of economic theory. This is the most important, but
difficult stage, because it requires digging out as much relevant variables
as possible with less if possible with no collinearity1 among the variables.
However, the model may be incorrectly specified due some reasons such
as omissions of one or more important variables, omissions of some
equations, incorrect mathematical form, etc.
1.3. Methodology of Econometrics
3. Specification of the Econometric Model
Even if we did our best to incorporate all the relevant variables, our
model will not be free from defect. There might be due to omission of
some unobserved variables, or errors of measurement, etc. Hence, as
explained in equation (1.1), we need stochastic variable 𝑢𝑖 to convert the
deterministic mathematical models in to probabilistic econometric model
there by accounting the effects of these random effects.
1.3. Methodology of Econometrics
4. Obtaining relevant data
To estimate the econometric model, that is, to obtain the numerical
values of estimators 𝛼o and 𝛼1, we need data.
5. Estimation of the Econometric Model
Once we collect the data, our next task is to estimate the parameters of
the model (the consumption function in this case) using one of the
different estimation techniques such as MLM, OLS, or others2. For
example, our estimation result could be:
𝐶 = 300 + 0.75𝑌
6. Hypothesis Testing: Assuming that the fitted (estimated) model is a
reasonably good approximation of reality, we have to develop suitable
criteria to find out whether the magnitude and sign of the parameters is
1.3. Methodology of Econometrics
7. Forecasting or Prediction
If the chosen model does not refute the hypothesis or theory under
consideration, we may use it to predict the future value(s) of the
dependent, or forecast, the dependent variable on the basis of known or
expected future value(s) of the explanatory or predictor variable.
8. Use of the Model for Control or Policy Purposes
This is the last instrument for the ultimate goal of econometrics. If the
forecasting power of the model is strong and if, possibly, the model is
chosen from among the different competing models, policy makers may
employ the model as an aid for the precision of policy making process.
1.4. The Sources, Types and Nature of Data :
Economic data sets come in a variety of types. These types can be
obtained from different sources. Basically, there are three types of data.
A. Cross-sectional data
Cross-sectional data is a random sample. Each observation is a new
individual, households, firm, etc with information at a given point in
time. For example, the data collected on the today’s consumption choices
and related issues of management students of University of Gondar is
cross sectional data.
B. Time Series data
Time series data has a separate observation on variable/s for each time
period, such as quarterly yearly, semi-annually, etc. Example, data on
consumer price index, GDP of a nation, etc.
1.4. The Sources, Types and Nature of Data :
C. Pooled data
Pooled data has both cross-sectional and time series features. If cross
sectional data on similar observations is collected/treated in different
times, it is called panel or longitudinal data. Panel data is a special form
of pooled data. Basically, pooled data increases sample size, and this is
the advantage of using pooled data.
