ECONOMETRICS I

Third Year
Economics Department
2024/2025
Pre- requisites

The course requires being familiar

with the material taught in the
Statistics for Economists (2), in
particular:

Basic concepts of regression analysis

Outline

1-Simple regression model

2- Multiple regression model
3- Dummy Variables
Relaxing the assumptions:
4- Multicollinearity
5- Heteroscedasticity
6- Autocorrelation
3
 Readings and Software

• D. N. Gujarati and D. C. Porter, (2009). "Basic

Econometrics", New York: McGraw-Hill, Inc.
• J. Wooldridge, (2003). “Introductory Econometrics: A
Modern Approach”, USA: Thomson, South-Wester.
• James Stock and Mark. M. Watson, Introduction to
Econometrics (3rd.edition update), Pearson, 2015.
• Lecture slides
• Stata

4
 Outline

Topic Reference
1. Simple regression model Gujarati (chapters 1-6)
2. Multiple regression model Gujarati (chapters 7,8)
3. Dummy variable regression model Gujarati (chapter 9)

Relaxing the assumptions

4. Multicollinearity Gujarati (chapter 10)
5. Heteroscedasticity Gujarati (chapter 11)
6. Autocorrelation Gujarati (chapter 12)
 Grades

To get the course credits:

1. One mid-term exam (20 points).
2. Two quizzes (20 points)
3. One assignment (10 points)
4. Final exam (50 points).
Examples
 Types of data

• Time series data

A set of observations of the values that a variable
takes at different time points (daily, weekly,
monthly, quarterly, annually,…)
• Cross sectional data
Data for one or variables are collected for
different observation units at the same point in
time.
• Panel data A combination of time series and
cross-sectional data.
11
Simple Regression
Model
 Regression Analysis
Regression analysis is used to predict the value of one variable (the
dependent variable) based on other variables (the independent
variables or explanatory variables).

Dependent variable: denoted Y

Independent variables: denoted X2, X3, …, Xk
If we have only ONE independent variable, the model will be

Yi = β1 + β2Xi + ui

which is referred to as simple linear regression. We would be

interested in estimating β1 and β2 from the data we collect.
 A HYPOTHETICAL EXAMPLE

• Regression analysis is largely concerned with estimating

and/or predicting the (population) mean value of the
dependent variable based on the known or fixed values of the
explanatory variable(s).
• Look at table 2.1 which refers to a total population of 60
families and their income (X) and consumption expenditure
(Y). The 60 families are divided into 10 income groups.
• There is considerable variation in consumption expenditure
in each income group. But the general picture that one gets is
that, despite the variability of consumption expenditure
within each income bracket, on the average, consumption
expenditure increases as income increases.
 The population regression line

• The dark circled points in Figure 2.1 show the

conditional mean values of Y against the various X
values. If we join these conditional mean values, we
obtain what is known as the population regression line
(PRL), or more generally, the population regression
curve. More simply, it is the regression of Y on X. The
adjective “population” comes from the fact that we
are dealing in this example with the entire population
of 60 families. Of course, in reality a population may
have many families.
 We can express the deviation of an individual Yi around
its expected value as follows:
ui = Yi − E(Y | Xi)
or
Yi = E(Y | Xi) + ui (2.4.1)
The Technically, ui is known as the stochastic disturbance or
stochastic error term.
population • How do we interpret (2.4.1)?
regression The expenditure of an individual family, given its income
level, can be expressed as the sum of two components:
line (1) E(Y | Xi), the mean consumption of all families
with the same level of income. This component is
known as the systematic, or deterministic, component,
(2) ui, which is the random, or nonsystematic,
component.

The disturbance term ui is a proxy for all those variables

that are omitted from the model but that collectively
affect Y. we don’t introduce them into the model
explicitly.
 Yi = β1 + β2Xi + ui
The
Yi = E(Y | Xi) + ui
population
regression
E(Y | Xi) = β1 + β2Xi
line
Ui = Yi − E(Y | Xi)
Sample Regression Function (SRF)
We can develop the concept of the sample regression function (SRF) to represent
the sample regression line.
Yˆi = βˆ1 + βˆ2Xi
where Yˆ is read as “Y-hat’’
Yˆi = estimator of E(Y | Xi)
βˆ1 = estimator of β1
βˆ2 = estimator of β2
uˆi = Yi − Yˆi (1)
Yi = Yˆi + uˆi (2)
Yi = βˆ1 + βˆ2Xi +uˆi (3)

ˆui denotes the (sample) residual term. Conceptually ˆui is analogous to ui and can
be regarded as an estimate of ui. It is introduced in the SRF for the same reasons
as ui was introduced in the PRF.
Least squares method minimizes the sum of squares of
residuals (deviations of individual data points from the
regression line)
ˆui = (Yi − Yˆi)
ˆu2i = (Yi − Yˆi)2
= (Yi − βˆ1 − βˆ2Xi)2
 THE ASSUMPTIONS UNDERLYING THE
METHOD OF LEAST SQUARES

Look at the PRF: Yi = β1 + β2Xi + ui . It shows that Yi depends on

both Xi and ui . The assumptions made about the Xi variable(s)
and the error term are extremely critical to the valid
interpretation of the regression estimates.

Classical linear regression model (CLRM), makes 10

assumptions.
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
Assumption No (9) the regression model is correctly specified
means that:

1- It contains the relative variables according to the economic theory , for example
the demand function must contains the price of the commodity and the price of other
goods. for example, if we ignored the variable of the price of the other goods, so the
model will not be correctly specified.
2- It uses the correct functional form, for example
Suppose the “true’’ or correct model in a cost-output study is as
follows:
Marginal costi = β1 + β2 outputi + β3 output2i + ui (1)
but we fit the following model:
Marginal costi = α1 + α2 outputi + ui (2)
So, model (2) uses the wrong functional form, so model (2) is not
correctly specified, but model (1) is correctly specified.
THE CLASSICAL LINEAR REGRESSION MODEL: THE
ASSUMPTIONS UNDERLYING THE METHOD OF LEAST
SQUARES
• If there is perfect linear relationship between X2 & X3 in this
case, we can not estimate the regression model.
• So, the classical linear regression model assumes that there is no
perfect multicollinearity or no perfect linear relationship
between the explanatory variables to be able to estimate the
regression model or to estimate the parameters
Note that: this assumption related to the linear relationship bet.
explanatory variables
So, if there is nonlinear relationship we can estimate the regression
model and there is no any problem.
PROPERTIES OF LEAST-SQUARES ESTIMATORS:
THE GAUSS–MARKOV THEOREM

To understand this theorem, we need to consider the best linear

unbiasedness property of an estimator. An estimator, say the OLS
estimator βˆ2, is said to be a best linear unbiased estimator (BLUE) of
β2 if the following hold:
1. It is linear, that is, a linear function of a random variable, such as
the dependent variable Y in the regression model.
2. It is unbiased, that is, its average or expected value, E(βˆ2), is equal
to the true value, β2.
3. It has minimum variance in the class of all such linear unbiased
estimators; an unbiased estimator with the least variance is known as
an efficient estimator.