Econometrics

By:
shafe z. (MSc. In Agricultural Economics)
 Chapter 1

Introduction to Econometrics
1.1. Definition and Scope of econometrics

? Econometrics

Econometrics means economic measurement.

It deals with measurement of economic relationships between
economic variables (dependent & independent variables).
Econometrics may be defined as the quantitative analysis of
actual economic phenomena based on the concurrent develop-
ment of theory and observation, related by appropriate methods
of inference (P. Samuelson).
It is concerned with the empirical determination of
economic laws.
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 (Goldberger, 1964).

a. Economic theory- states a qualitative relation-

ship between economic variables.

Ex.1. Microeconomic theory states that, other things

remaining the same, a reduction in the price of a
commodity is expected to increase the quantity de-
manded of that commodity.
Thus, economic theory postulates a negative or in-
verse relationship between the price and quantity
demanded of a commodity.

Ex.2. Consumption depends up on current income

(Yt) & previous income (Yt-1) of an individual other
things being constant.
The theory itself does not provide any numerical
measure of the relationship between the variables.
b. Mathematics– its main concern is to express the
economic theory in mathematical form (equa-
tions).
We can explain the above theoretical relationship in
mathematical form /example 2/ as follows

Where Ct: consumption expenditure, Yt: current in-

come & Yt-1: previous income
Again this mathematical relation does not capture

other factors that affect consumption expenditure.

c. Statistics- It is mainly concerned with collecting,

processing and presenting economic data in the
form of charts and tables
Thus, econometrics integrates those 3 disciplines
 Estimation of economic parameters (elasticities)

 Predicting economic outcomes

 Testing economic outcomes

 1.2. Goals of Econometrics
1. Analysis
aims primarily at the verification of Economic/econometric
theories & there by to know & decide how well they explain
the observed behavior of the economic units.

2. Policy making
supplying numerical estimates of the coefficients of eco-
nomic relationships, which may be then used for decision
making

3. Forecasting
using the numerical estimates of the coefficients in order to
forecast the future values of the economic magnitudes
These goals are not mutually exclusive

Successful econometric applications should include

the combinations of all three aims
 1.3. Methodology of Econometrics
 In any econometrics research we may distinguish the follow-

ing steps.
1. Economic theory or hypothesis

 Keynes stated that Consumers increase their consump-

tion as their income increases, but not by as much as the

increase in their income

 In short, marginal propensity to consume (MPC), the

rate of change of consumption for a unit (say, a dollar)

change in income, is greater than zero but less than 1.

2. Specification of the Mathematical Model
Although Keynes postulated a positive relationship between
consumption and income, he did not specify the precise form
of the functional relationship between the two.
For simplicity, a mathematical economist might suggest the fol-
lowing form of the Keynesian consumption function:

 where Y = consumption expenditure and X = income, and where

β1 and β2 known as the parameters of the model.
 The slope coefficient β2 measures the MPC and β1 is the inter-
cept.
3. Specification of the Econometric Model
 The purely mathematical model of the consumption func-
tion assumes that there is an exact or deterministic rela-
tionship between consumption and income.
 But relationships between economic variables are gener-
ally inexact because, in addition to income, other variables
affect consumption expenditure.
 For example, size of family, ages of the members in the
family, family religion, etc. are likely to exert some influ-
ence on consumption.
 To allow for the inexact relationships between economic vari-
ables, the econometrician would modify the deterministic
consumption function as follows:

 where u, known as the disturbance, or error, term, is a ran-

dom (stochastic) variable that has well-defined probabilistic
properties.
The disturbance term u may well represent all those factors
that affect consumption but are not taken into account ex-
plicitly.
 Types of data
4. Obtaining Data
To estimate the econometric model (to obtain the numerical val-
ues of β1 and β2) we need data.
a. Cross-section data- Many units observed at one point in time
Examples include individual Census or survey respondents, states or
countries, students, colleges, etc.
b. Time-series data- Same unit observed at many points in time
(usually equally spaced)
Examples include national macroeconomic variables

c. Pooled data: Observations both over time and across units, but
not necessarily the same units in each time period
d. Panel (longitudinal) data - Special case of pooled data
Multiple (same) units observed at multiple points in time

 Examples include state-level or national-level time-series data

(for many states or countries), many colleges observed over

time.

5. Estimation of the Econometric Model

 Determining(estimating) the numerical values of the parame-
ters(β1 and β2).
In our example, depending on the data we can estimate the
numerical values of the parameters consumption function us-
ing an econometric model called regression analysis.

The hat on the Y indicates that it is an estimate.

6. Hypothesis Testing
Assuming that the fitted model is a reasonably good approxi-
mation of reality, we have to develop suitable criteria to find
out whether the estimates obtained in the previous example
are in accordance with the expectations of the theory that is
being tested.
In our example we found the MPC to be about 0.70. But
before we accept this finding as confirmation of Keyne-
sian consumption theory, we must enquire whether this
estimate is sufficiently below unity to convince us that
this is not a chance occurrence or peculiarity of the par-
ticular data we have used.

In other words, is 0.70 statistically less than 1? If it is, it

may support Keynes’ theory.

Such confirmation or refutation of economic theories on

the basis of sample evidence is based on a branch of sta-
tistical theory known as statistical inference (hypoth-
esis testing).
Evaluation criteria of estimates may be classified into

three groups:
 Economic a priori criteria- which are determined
by economic theory
 Statistical criteria- determined by statistical theory

 Econometric criteria - determined by econometric

theory
Economic theory defines the signs of these coeffi-

cients and their magnitude.

If the estimates of the parameters turn up with

signs or size not conforming to economic the-

ory, they should be rejected,

 unless there is good reason to believe that in

the particular instance the principle of eco-

nomic theory does not hold.
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, variable Y on the basis of known or expected
future value(s) of the explanatory, or predictor, vari-
able X.
8. Use of the Model for Control or Policy Purposes
This means by applying different methods of econo-
metrics techniques we can obtain individual numerical
values for the coefficients of economic relationship.

Using these numerical values a decision can be under-

taken by different economic agents.

Econometrics can supply MPC, elasticties, MC, MR etc.

Using these magnitudes (numerical values) decision

will be undertaken.
 1.4. Components of Econometrics
 Econometric inputs:
 Economic Theory
 Mathematics
Statistics
 Data
 Computers (CPU power)

 Econometric outputs:
 Estimation - Measurement
 Inference - Hypothesis testing
 Forecasting - Prediction
 1.5. Types of Econometrics
1. Theoretical Econometrics: - It is concerned with the devel-
opment of appropriate econometric methods for measuring
economic relationship.
 For example one of the methods is Least squares.

2. Applied Econometrics:- This is the application of theoretical

Econometrics methods to the specific branch of economic
theory
 i.e. application of theoretical Econometrics for verification &
forecasting of demand, cost, supply, production, investment,
consumption & other related field of economic theory.
 Chapter 2

Correlation Theory
2.1. Definition and meaning of Correlation
Correlation is a statistical tool that helps to measure
and analyze the degree of relationship between two or
more variables.
Correlation analysis deals with the association be-
tween two or more variables.
Measures the relative strength of the linear relation-
ship between two variables - Unit-less
The correlation analysis enable us to have an idea
about the degree & direction of the relationship be-
tween the two or more variables under study.
The measure of correlation is called the correlation co-

efficient (r).
The degree of relationship is expressed by coefficient

which range from -1 to +1.

The direction of relationship is indicated by a sign of r.

The closer to –1, the stronger the negative linear rela-

tionship
The closer to 1, the stronger the positive linear rela-

tionship
The closer to 0, the weaker the linear relationship
 Types of Correlation
Type I

Correlation

Positive Correlation Negative Correlation

 Positive Correlation: The correlation is said to be positive correlation if

the values of two variables changing with same direction.

Ex. Income and consumption.

 As X is increasing, Y is increasing
 As X is decreasing, Y is decreasing
Indicated by sign; (+)
 E.g., As height increases, so does weight.

 Negative Correlation: The correlation is said to be negative correlation

when the values of variables change with opposite direction.

Ex. Price & qty. demanded.

 As X is increasing, Y is decreasing
 As X is decreasing, Y is increasing Indicated by sign; (-).
 E.g., As TV time increases, grades decrease
 More examples

Positive relationships Negative relationships:

water consumption and tem- alcohol consumption and

perature. driving ability.

study time and grades. Price & quantity demanded

 Types of Correlation
Type II

Correlation

Simple Multiple

Partial Total
Simple correlation: Under simple correlation problem only

two variables are studied. E.g. water consumption and tem-

perature.
Multiple Correlation: Under Multiple Correlation three or

more than three variables are studied.

Ex. Qd = f ( P, PC , PS , t, y )

 Partial correlation: analysis recognizes more than two

variables but considers only two variables keeping the

other constant.
 Total correlation: is based on all the relevant variables,

which is normally not feasible.

 Types of Correlation
Type III

Correlation

Linear Non Linear

Linear correlation: Correlation is said to be linear when

the amount of change in one variable tends to bear a con-

stant ratio
X 1 to2the3amount
4 5of change
6 7 in8 the other.
Y 5 7 9 11 13 15 17 19 Y = 3 + 2x
Ex

Non Linear correlation: The correlation would be non lin-

ear if the amount of change in one variable does not bear a

constant ratio to the amount of change in the other vari-

Methods of Studying Correlation
Scatter Diagram Method
Karl Pearson’s Coefficient of Correlation
Spearman rank correlation coefficient
Kendal rank correlation coefficient

a. Scatter Diagram Method

Scatter Diagram is a graph of observed plotted points
where each points represents the values of X & Y as a coor-
dinate.
It portrays the relationship between these two variables
graphically.
 A perfect positive correlation
Weight
Weight
of B
Weight A linear
of A
relationship

Height
Height Height
of A of B
High Degree of positive correlation
Positive relationship

r = +.80

Weight

Height
 Degree of correlation
Moderate Positive Correlation

r = + 0.4
Shoe
Size

Weight
 Degree of correlation
Perfect Negative Correlation

r = -1.0
TV watch-
ing per
week

Exam score
 Degree of correlation
Moderate Negative Correlation

r = -.80
TV
watching
per
week

Exam score
 Degree of correlation
Weak negative Correlation

Shoe
r = - 0.2
Size

Weight
 Degree of correlation
No Correlation (horizontal line)

r = 0.0
IQ

Height
r = +.80 r = +.60

r = +.40 r = +.20
 b. Karl Pearson's Coefficient of Correlation

Pearson’s ‘r’ is the most common correlation coefficient.

Karl Pearson’s Coefficient of Correlation denoted by- ‘r’

- measure the degree of linear relationship between two vari-

ables say x & y.
Karl Pearson’s Coefficient of Correlation denoted by- r

-1 ≤ r ≤ +1
 Degree/ strength of Correlation is expressed by a value of
Coefficient
Direction of change is Indicated by sign (- ve) or ( + ve)
Pearson’s “r”
SSX   

X i2
X  i
2

n
SCP
r (  Yi ) 2
( SSX )( SSY ) SSY  Yi
2

n

SCP   X Y 
i i
 X Y i i

n
 Calculating by hand…

 ( x  x )( y
i 1
i i  y)
cov ariance( x, y ) n 1
rˆ  
var x var y n n

 (x  x)  ( y
i 1
i
2

i 1
i  y) 2

n 1 n 1
Simpler calculation formula…

 ( x  x )( y  y )
i 1
i i

Numerator of
rˆ  n 1 
n n covariance
 i
( x  x ) 2
 i
( y  y ) 2

i 1 i 1 SS xy
n 1 n 1 rˆ 
n SS x SS y
 ( x  x )( y  y )
i i
SS xy
i 1

n n
SS x SS y
 (x  x)  ( y  y)
i 1
i
2

i 1
i
2 Numerators
of variance
 Procedure for computing the correlation coefficient

Calculate the mean of the two variables ‘x’ & ’y’

Calculate the deviations ‘x’ &’y’ in two series from their re-

spective mean.
Square each deviation of ‘x’ &’y’ then obtain the sum of the

squared deviation i.e.∑x2 & .∑y2

Multiply each deviation under x with each deviation under y

& obtain the product of ‘xy’. Then obtain the sum of the
product of x , y i.e. ∑xy
Substitute the value in the formula.
Example

Below are the data for six participants giving their number of years in

college (X) and their subsequent yearly income (Y).

No Years in college (X) Yearly income (Y)

1 0 15
2 1 15
3 3 20
4 4 25
5 4 30
6 6 35
Determine Pearson's coefficient of correlation?
 Hypothesis testing

Step 1: State the Hypotheses

H0: The correlation between years of education and income is

equal to zero in the population.

H1: The correlation between years of education and income

not equal to zero in the population.

Step 2: Find the Critical Value
Locate the table, and find the degrees of freedom for the ap-

propriate test to find the critical value.

Step 3: Run the Statistical Test

Standard error of correlation coefficient:

1 r2
SE ( rˆ) 
n2
Step 4: Make a Decision about the Null hypothesis

•Reject or accept the null depending on the value we computed in

Step 3 and critical value in Step 2.

Step 5: Write a Conclusion

There is a relationship between variables or not.

The sample correlation coefficient follows a T-

distribution with n-2 degrees of freedom (since

you have to estimate the standard error).

*note, like a proportion, the variance of the cor-

relation coefficient depends on the correlation

coefficient itself  substitute in estimated r
 Interpretation of Correlation Coefficient (r)

The value of correlation coefficient ‘r’ ranges from -

1 to +1
If r = +1, then the correlation between the two vari-

ables is said to be perfect and positive

If r = -1, then the correlation between the two vari-

ables is said to be perfect and negative

If r = 0, then there exists no correlation between the

variables
 Assumptions of Pearson’s Correlation Coefficient

There is linear relationship between two variables, i.e. when

the two variables are plotted on a scatter diagram a straight line

will be formed by the points.

Advantages of Pearson's coefficient

It summarizes in one value, the degree of correlation & direc-

tion of correlation also.

 Limitation of Pearson’s Coefficient

Always assume linear relationship

Value of Correlation Coefficient is affected by the

extreme values.

Time consuming methods

 c. Spearman’s Rank Coefficient of Correlation

When statistical series in which the variables under study

are not capable of quantitative measurement but can be

arranged in serial order, in such situation pearson’s corre-

lation coefficient can not be used in such case Spearman

Rank correlation can be used.

when variables are not normally distributed,

but their values can be ranked

r s = Rank correlation coefficient

Di = Difference of rank between paired item in

two series.

n = Total number of observation.

 Interpretation of Rank Correlation Coefficient (R)

The value of rank correlation coefficient, R ranges from -1

to +1

If R = +1, then there is complete agreement in the order of

the ranks and the ranks are in the same direction

If R = -1, then there is complete agreement in the order of

the ranks and the ranks are in the opposite direction

If R = 0, then there is no correlation

 Rank Correlation Coefficient (R)

a) Problems where actual rank are given.

1) Calculate the difference ‘D’ of two Ranks i.e. (R1 – R2).

2) Square the difference & calculate the sum of the difference

i.e. ∑D2

3) Substitute the values obtained in the formula.

b) Problems where Ranks are not given: If the ranks are

not given, then we need to assign ranks to the data series.

The lowest value in the series can be assigned rank 1 or the

highest value in the series can be assigned rank 1. We need

to follow the same scheme of ranking for the other series.

 Then calculate the rank correlation coefficient in similar

way as we do when the ranks are given.