Econometrics
Econ. 405
Chapter 2:
Steps of Econometric Analysis
Steps of econometric analysis
Traditional econometric methodology proceeds
along the following lines:
1. Statement of theory or hypothesis.
2. Specification of the mathematical model of the
theory (Economic Model)
3. Collecting the data
4. Specification of the statistical, or econometric
model
5. Estimation of the parameters of the econometric
model
6. Hypothesis testing
7. Using the model for control or policy purposes.
1. Statement of theory or hypothesis.
on average, Kuwaiti consumers increase their
consumption of goods and services as their
incomes increase
2. Specification of the mathematical model of the
theory (Economic Model)
Y = β1 + β2 X
0 < β2 < 1
Y = consumption expenditure (dependent variable)
X = income (independent, or explanatory variable)
β1 = the intercept
β2 = the slope coefficient
The slope coefficient β2 measures the MPC in this
case.
Illustrate Geometrically the relationship between
Consumption (Y) and Income (X):
3. Collecting the data
4. Specification of the statistical (econometric model)
The mathematical (economic) model is modified as :
Y = β1 + β2X + u
Consumption = β1 + β2 Income + u
Note: The relationships between economic variables are
generally inexact. In addition to income, other variables
affect consumption expenditure. For example, size of family,
ages, gender, etc., are likely to have some influence on
consumption.
Thus: term “u” is known as the disturbance (error term), is
a random (stochastic) variable that has well-defined
probabilistic properties. The disturbance term “u “ may well
represent all those factors (size of family, ages, behavior,
etc) that affect consumption but are not taken into account
explicitly.
The relationship between Consumption (Y) and Income (X) is
a linear regression model( i.e., it hypothesizes that Y is
linearly related to X), but that the relationship between the
two is not exact; it is subject to individual variation:
5. Estimation of parameters of econometric model
Regression analysis uses an econometrics software to
obtain estimates. Using this technique and the data
given, we obtain the following estimates of β1 and β2,
namely, −184.08 and 0.7064. Thus, the estimated model
is:
Yˆ = −184.08 + 0.7064Xi
 The estimated regression line is shown in the
following Figure. The regression line fits the data
quite well. The slope coefficient (i.e., MPC) was
about 0.70.
 β2 states that an increase in income by 1 KD led, on
average, to an increase consumption by 700 Files (Or,
if income increases by 1 unit, consumption increases
by 70%.
The econometrics model is now plotted the following
estimated regression line :
Y
X
6. Hypothesis Testing
A- Significance of the findings (estimates )
 It is the most common expression used when
dealing with quantitative methods.
 Here, the slopes (β’s) are the focus.
 Statistically significant refers to the case that the
relationship is unlikely due to chance ( probably
true)
 There are several ways to determine the
significance of the result ( t-test, P-value, Ftest….etc.)
B- Consistency of the findings (estimates )
The question :
DOES your result (estimated parameters) make
sense?
The Answer :
Check what the theory says.
In this example:
Theory: Keynes expected MPC to be positive but less
than 1
Findings: MPC to be positive and about 0.70
7. Using the model for control or policy purposes
 The question :
DOES your result (estimated parameters) reveal any policy
implications?
 The Answer :
Depends on how readable they are !!
In this example:
Findings: People of Kuwait spend more when they have higher
incomes
Policy implication: if the government wants to reduce inflation
they might think of reducing spending by public, this is can be
done through influencing their income. Then the solution is to tax
them !!
Note: Policy implication should be linked to your findings.