Introduction to Econometrics for Finance

 Course Title : Introduction to Econometrics for Finance

 Ac/d Year: 2013E.C.

 Offered to: MSc Acct 

 Course code: Econ 552

 Credit hour: 3

 Course outline

 Semester: 1st

 Course Instructor: Amare M.(PhD)

By: Amare Mitiku
 Course Outline
COURSE DESCRIPTION
2
This course focuses on the financial applications of econometric techniques.

Econometrics students need to have such knowledge to

 test theories in finance,

 estimate asset prices or returns,

 analyze the relationships between variables,

 forecast financial variables etc.

Decision making in business and economics is often supported by the use of quantitative information.

Econometrics is concerned with summarizing relevant data & information by means of a model.

Such econometric models help us to understand the relation between economic and business variables

and to analyse the possible effects of decisions.

By: Amare Mitiku

 cont....
3
It first makes an introduction to the basic concepts in

econometrics like economic and econometric modelling as

well as types of data; then proceeds to the simple classical

linear regression model.

Then introduce multiple regression techniques; the estimation

of regression using ordinary least squares; inference; and the

use of spreadsheets and statistical software to estimate

economic models.
By: Amare Mitiku
 Course Objective

 The goal of the course is to introduce

4 graduates with the theoretical
background and practical skills needed for understanding the
existing empirical studies as well as for carrying out their own
empirical work in Accounting and Finance.
 At the end of the course, graduates will be able to:
 Distinguish between economic and econometric models;
 Do simple and multiple regression with economic data (both manually and
using statistical packages);
 Interpret regression results (like coefficients and R2) and test hypotheses
and
 Detect (in) existence of problems of multicollinearity, heteroscedasticity
and autocorrelation as well as suggest how to rectify such problems.
 Identify the different statistical tools to be used to solve problems in the
area of Finance and investment.

By: Amare Mitiku

 Cont...
5
Chapters Chapters
 Chapter 1: Introduction to  Chapter 2: Estimation of Two Variable
Econometrics: Regression Model
1.1.The purpose and applications of 2.1. The method of OLS
2.2. The classical linear regression model
Econometrics
2.3. The assumptions
1.2. The kinds of problems handled by 2.4. Properties of least square estimates
econometrics 2.5. The coefficient of determination R2
and adjusted R2 (R2)
1.3.The link between economic theory
2.6. Hypothesis testing and confidence interval
mathematics, statistics and nometrics

By: Amare Mitiku

 Cont...
6

Chapters Chapters

 Chapter 3: Estimation of Multiple  Chapter 4: Problems of Measurement,

Specification, Estimation and Their Solutions:
Linear Regression Model

4.1. Heteroscedasticity
3.1. The three variable model notation
and assumptions 4.2. Autocorrelation
3.2. Interpretation of multiple regressions 4.3. Multicollinerity
4.4. Distributed lag models and Expectations

Chapter 5: Basic Understandings of Econometric

Software useful for mode building (STATA)

By: Amare Mitiku

 Cont....
7
Mode of Delivery
Lecture classes, assigned exercise and presentation of group practical exercises.
Modes of Evaluation
 Assignments 20%
 Midterm (Quizzes) 30%
 Final Exam 50%
TOTAL 100%

References
Jefferey M. Wooldridge (2002), Introductory Econometrics, A modern Approach, by 2 nd
edition.
Christiaan, BoerPhilip, HFranses, Kloek, and van Dijk, (2007). Econometric Methods with
Applications in Business and Economics, Oxford University press, 1 st edition.
Dominick Salvatore, & Derrck Reagle (2002), Statistics and Econometrics, 2nd edition, Mc
Graw Hill.
Greene, W., (2003), Econometric Analysis, Prentice Hall, 3 rd edition.
Gujarati, D.N., (2009), Basic Econometrics, Mc Graw Hill, New York, 54 th edition.

By: Amare Mitiku

 Introduction to Econometrics for Finance
8
Definition and scope of econometrics
Economics is full of the complex relationships between variables with their

own specified functions.

As economists, we may be interested in questions such as: If one variable

changes in a certain magnitude, by how much will another variable change?

Also, given that we know the value of one variable; can we forecast or

predict the corresponding value of another?

The purpose of studying the relationships among economic variables and

attempting to answer questions of the type raised here, is to help us

understood the real economic world we live in.
By: Amare Mitiku
 Cont..
9
 However, economic theories that postulate the relationships

between economic variables have to be checked against data

obtained from the real world.
 If the empirical data verify the relationship proposed by

economic theory, we accept the theory as valid.

 If the theory is incompatible with the observed behaviour, we

either reject the theory or in the light of the empirical evidence

of the data, we ought to modify the theory.

By: Amare Mitiku

 Cont...
10
 To provide a better understanding of economic relationships and a
better guidance for economic policy making ,we also need to
know the quantitative relationships between the different
economic variables.

We obtain these quantitative measurements taken from the real

world.
The field of knowledge which helps us to carryout such an
evaluation of economic theories in empirical terms is
econometrics.

By: Amare Mitiku

 Cont...
 What is the importance of studying Econometrics
11 for you Accoutants?
 What is Econometrics?

 Literally interpreted, econometrics means “economic

measurement”, but the scope of econometrics is much broader
as described by leading econometricians.
 Various econometricians used different ways of wordings to

define econometrics.
 Econometrics is the amalgamation of statistics and
mathematical Economics together with economic theories.
 In other words,
By: Amare Mitiku
 Cont...

 “Econometrics is the science 12

which integrates economic theory,
statistics for economists, and mathematical economics to investigate
the empirical support of economic theory.
 It is a special type of economic analysis and research in which the

general economic theories, formulated in mathematical terms, is

combined with empirical measurements of economic phenomena.
 Starting from the relationships of economic theory, we express them

in mathematical terms so that they can be measured.

 We then use specific methods, called econometric methods in order to

obtain numerical estimates of the coefficients of the economic

relationships.”
By: Amare Mitiku
 Cont...
 Measurement is an important aspect
13 of econometrics even though
the scope of econometrics is much broader than measurement.
 As it is rightly stated the “metric” part of the word econometrics

signifies ‘measurement’, and hence econometrics is basically

concerned with measuring of economic relationships.
 In sum, 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 and
verifying economic theories.

By: Amare Mitiku

 1.2 Econometrics vs. mathematical economics

14
 Mathematical economics states economic theory in terms of
mathematical symbols.
 There is no essential difference between mathematical economics
and economic theory.
 Both state the same relationships, but while economic theory uses
verbal exposition(words and sentences), mathematics uses
symbols and equations.
 Both express economic relationships in an exact or deterministic
form.
 Neither mathematical economics nor economic theory allows for
random elements which might affect the relationship and make it
stochastic.

By: Amare Mitiku

 Cont...

15

 Econometrics differs from mathematical economics in that, it does

not assume exact or deterministic relationship.

 Econometrics assumes also random/stochastic relationships among

economic variables.
 Econometric methods are designed to take into account random

disturbances which relate deviations from exact behavioural

patterns suggested by economic theory and mathematical
economics.

By: Amare Mitiku

 16 vs. statistics
1.3 Econometrics

 Econometrics differs from both mathematical economics and

economic statistics.
 An economic statistician gathers empirical data, records them,

tabulates them or charts them, and attempts to describe the pattern

in their development over time and perhaps detect some
relationship between various economic magnitudes.
 Economic statistics is mainly a descriptive aspect of economics.

 It does not measurements of the coefficients of economic

relationships.
By: Amare Mitiku
 Cont...
17
 Mathematical (or inferential) statistics deals with the method

of measurement which are developed on the basis of controlled

experiments.
 But 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.
By: Amare Mitiku
 Cont...
18
 Yet the fundamental ideas of inferential statistics are applicable

in econometrics, but they must be adapted to the problem of

economic life.
 Econometric methods are adjusted so that they may become

appropriate for the measurement of economic relationships

which are stochastic.
 The adjustment consists primarily in specifying the stochastic

(random) elements that are supposed to operate in the real

world and enter into the determination of the observed data.
By: Amare Mitiku
 1.4 Economic models vs. econometric
i) Economic models: models
19

 Any economic theory is an observation from the real world. For one

reason, the immense complexity of the real world economy makes it

impossible for us to understand all interrelationships at once.
 Another reason is that all the interrelationships are not equally

important as such for the understanding of the economic

phenomenon under study.
 The sensible procedure is therefore, to pick up the important factors

and relationships relevant to our problem and to focus our attention

on these alone.
By: Amare Mitiku
 Cont....
20
Such a deliberately simplified analytical framework is called
an economic model.
It is an organized set of relationships that describes the
functioning of an economic entity under a set of simplifying
assumptions.
All economic reasoning is ultimately based on models.
Economic models consist of the following three basic
structural elements.
1. A set of variables
2. A list of fundamental relationships
3. A number of strategic coefficients
By: Amare Mitiku
 ii) Econometric models:

21
 The most important characteristics of economic relationships is

that they contain a random element which is ignored by

mathematical economic models which postulate exact
relationships between economic variables.
 Example: Economic theory postulates that the demand for a

commodity depends on its price, on the prices of other related

commodities, on consumers’ income and on tastes.
 This is an exact relationship which can be written mathematically

as: Q=b0+b1P+b2P0+b3Y+b4t
By: Amare Mitiku
 Cont...
22
 The above demand equation is exact. However, many more factors may

affect demand.
 In econometrics the influence of these ‘other’ factors is taken into

account by the introduction into the economic relationships of random

variable.
 In our example, the demand function studied with the tools of

econometrics would be of the stochastic form:

Q=b0+b1P+b2P0+b3Y+b4t+u

where u stands for the random factors which affect the quantity
demanded.
By: Amare Mitiku
 1.5 Methodology of econometrics

23
 Econometric research is concerned with the measurement of the parameters of

economic relationships and with the predication of the values of economic variables.
 The relationships of economic theory which can be measured with econometric

techniques are relationships in which some variables are postulated as causes of the
variation of other variables.
 Starting with the postulated theoretical relationships among economic variables,

econometric research or inquiry generally proceeds along the following lines/stages.

1. Specification of the model

2. Estimation of the model
3. Evaluation of the estimates
4. Evaluation of he forecasting power of the estimated model
By: Amare Mitiku
 1. Specification of the model
24

In this step the econometrician has to express the relationships between
economic variables in mathematical form.
This step involves the determination of three important tasks:
i) the dependent and independent (explanatory) variables which will be included
in the model.
ii) the a priori theoretical expectations about the size and sign of the parameters of
the function.
iii) the mathematical form of the model (number of equations, specific form of the
equations, etc.)
Note: The specification of the econometric model will be based on economic
theory and on any available information related to the phenomena under
investigation.
Thus, specification of the econometric model presupposes knowledge of
economic theory and familiarity with the particular phenomenon being studied.
By: Amare Mitiku
 Cont...
25
Specification of the model is the most important and the most difficult stage of any
econometric research.
It is often the weakest point of most econometric applications.
In this stage there exists enormous degree of likelihood of committing errors or
incorrectly specifying the model.
Some of the common reasons for incorrect specification of the econometric models
are:
1. the imperfections, looseness of statements in economic theories.
2. the limitation of our knowledge of the factors which are operative in any particular
case.
3. the formidable obstacles presented by data requirements in the estimation of large
models.
The most common errors of specification are:
a. Omissions of some important variables from the function.
b. The omissions of some equations (for example, in simultaneous equations model).
c. The mistaken mathematical form of the functions.
By: Amare Mitiku
 Cont...
2. Estimation26of the model

This is purely a technical stage which requires knowledge of the various

econometric methods, their assumptions and the economic implications for the

estimates of the parameters.

 This stage includes the following activities.

a. Gathering of the data on the variables included in the model.

b. Examination of the identification conditions of the function

(especially for simultaneous equations models).

c. Examination of the aggregations problems involved in the

By: Amare Mitiku
variables of the function.
 Cont...
27

d. Examination of the degree of correlation between the

explanatory variables (i.e. examination of the problem of

multicollinearity).

e. Choice of appropriate economic techniques for estimation,

i.e. to decide a specific econometric method to be applied

in estimation; such as, OLS, MLM, Logit, and Probit.

By: Amare Mitiku

 3. Evaluation of the estimates

28
This stage consists of deciding whether the estimates of
the parameters are theoretically meaningful and
statistically satisfactory.
This stage enables the econometrician to evaluate the
results of calculations and determine the reliability of the
results.
For this purpose we use various criteria which may be
classified into three groups:
i. Economic a priori criteria:
These criteria are determined by economic theory and
refer to the size and sign of the parameters of economic
relationships.
By: Amare Mitiku
 Cont...
29

ii. Statistical criteria (first-order tests): These are

determined by statistical theory and aim at the
evaluation of the statistical reliability of the estimates
of the parameters of the model.
Correlation coefficient test, standard error test, t-test, F-
test, and R2-test are some of the most commonly used
statistical tests.

By: Amare Mitiku

 Cont...
30
iii. Econometric criteria (second-order tests):
 These are set by the theory of econometrics and aim at the
investigation of whether the assumptions of the econometric method
employed are satisfied or not in any particular case.
 The econometric criteria serve as a second order test (as test of the

statistical tests) i.e. they determine the reliability of the statistical

criteria; they help us establish whether the estimates have the
desirable properties of unbiasedness, consistency etc.
 Econometric criteria aim at the detection of the violation or validity

of the assumptions of the various econometric techniques.

By: Amare Mitiku
 Cont...
31

4) Evaluation of the forecasting power of the model:

Forecasting is one of the aims of econometric
research. However, before using an estimated
model for forecasting by some way or another the
predictive power of the model.
It is possible that the model may be economically

By: Amare Mitiku

 Cont...
32

meaningful and statistically and econometrically

correct for the sample period for which the model has
been estimated; yet it may not be suitable for
forecasting due to various factors (reasons).
Therefore, this stage involves the investigation of the
stability of the estimates and their sensitivity to
changes in the size of the sample.
 Consequently, we must establish whether the
estimated
function performs adequately outside the sample of
data. i.e. we must test an extra sample performance the
model.
By: Amare Mitiku
 1.6 Desirable properties of an econometric model
 An econometric model is a model whose parameters have been
33
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. It must describe adequately the
economic phenomena to which it relates.
2. Explanatory ability. The model should be able to explain the
observations of he actual world. It must be consistent with the
observed behaviour 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 he structural
By:model.
Amare Mitiku
 Cont...
34

 The estimates should if possible possess the desirable properties

of unbiasedness, consistency and efficiency.
4. Forecasting ability. The model should produce satisfactory
predictions of future values of he dependent (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 (that is to say
provided that the other desirable properties are not affected by
the simplifications of the model).

By: Amare Mitiku

 1.7 Goals of Econometrics
35
 Three main goals of Econometrics are identified:

i) Analysis i.e. testing economic theory

ii) Policy making i.e. Obtaining numerical estimates of the
coefficients of economic relationships for policy simulations.

iii) Forecasting i.e. using the numerical estimates of the

coefficients in order to forecast the future values of economic

magnitudes.

By: Amare Mitiku

 1.8. Structure of Economic Data
36

 Economic data sets come in a variety of types.

 We describe the most important data structures encountered in applied work.
 1. Cross-sectional Data
 A cross-sectional data set consists of a sample of individuals, households,
firms, cities, states, countries, or a variety of other units, taken at a given
point in time.
 Sometimes, the data on all units do not correspond to precisely the same time
period.
 For example, several families may be surveyed during different weeks within
a year.
 In a pure cross-sectional analysis, we would ignore any minor timing
differences in collecting the data.
 If a set of families was surveyed during different weeks of the same year, we
would still view this as a cross-sectional data set.
By: Amare Mitiku
 Cont...
37

An important feature of cross-sectional data is that we can

often assume that they have been obtained by random
sampling from the underlying population.
For example, if we obtain information on wages,
education, experience, and other characteristics by
randomly drawing 500 people from the working
population, then we have a random sample from the
population of all working people.

By: Amare Mitiku

 Cont....
38

Obsno wage exper educ female married

1 3.10 11 2 1 0
2 3.24 12 22 1 1
3 3.00 11 2 0 0
4 6.00 8 44 0 1
5 5.30 12 7 0 1
..... ..... .... .... .... .....
450 11.56 16 5 0 1
500 3.50 14 5 1 0

By: Amare Mitiku

 2. Time Series data
39

 A time series data set consists of observations on a variable or several variables over
time.
 Examples of time series data include stock prices, money supply, consumer price
index, gross domestic product, annual homicide rates, and automobile sales figures.
 Because past events can influence future events and lags in behaviour are prevalent in
the social sciences, time is an important dimension in a time series data set.
 Unlike the arrangement of cross-sectional data, the chronological ordering of
observations in a time series conveys potentially important information.
 A key feature of time series data that makes them more difficult to analyze than cross-
sectional data is that economic observations can rarely, if ever, be assumed to be
independent across time.
 Most economic and other time series are related, often strongly related, to their recent
histories.
 For example, knowing something about the gross domestic product from last quarter
tells us quite a bit about the likely range of the GDP during this quarter, because GDP
tends to remain fairly stable from one quarter to the next.
By: Amare Mitiku
 Cont....
40

Although most econometric procedures can be used with

both cross-sectional and time series data, more needs to be
done in specifying econometric models for time series data
before standard econometric methods can be justified.
In addition, modifications and embellishments to standard
econometric techniques have been developed to account for
and exploit the dependent nature of economic time series and
to address other issues, such as the fact that some economic
variables tend to display clear trends over time.
Another feature of time series data that can require special
attention is the data frequency at which the data are collected.
By: Amare Mitiku
 Cont...
41

In economics, the most common frequencies are daily,

weekly, monthly, quarterly, and annually. Stock prices are
recorded at daily intervals (excluding Saturday and Sunday).
The money supply in the U.S. economy is reported weekly.
Many macroeconomic series are tabulated monthly, including
inflation and unemployment rates.
Other macro series are recorded less frequently, such as every
three months (every quarter). Gross domestic product is an
important example of a quarterly series. Other time series,
such as infant mortality rates for states in the United States,
are available only on an annual basis.

By: Amare Mitiku

 Cont....
42

Obsno year avgmin avgcon unemp gnp

1 1950 0.20 20.1 15.4 879.3
2 1951 0.21 20.6 16.8 916.5
3 1952 0.23 22.7 14.4 1053.1
4 1953 0.36 24.5 17.9 1127.8
...... ...... ..... .... .... ....
466 2014 3.35 58.1 18.7 4317.2
500 2015 3.35 58.2 23.6 4478.9
The variable avgmin refers to the average minimum wage for the year, avgcov is
the average coverage rate (the percentage of workers covered by the minimum
wage law), unemp is the unemployment rate, and gnp is the gross national
product. We will use these data later in a time series analysis of the effect of the
minimum wage on employment.

By: Amare Mitiku

 3.Panel or Longitudinal Data
43

A panel data (or longitudinal data) set consists of a time series for
each cross-sectional member in the data set.
As an example, suppose we have wage, education, and
employment history for a set of individuals followed over a ten-
year period.
Or we might collect information, such as investment and
financial data, about the same set of firms over a five-year time
period.
Panel data can also be collected on geographical units.
For example, we can collect data for the same set of regions in the
Ethiopia on immigration flows, tax rates, wage rates, government
expenditures, and so on, for the years 1990, 2000, and 2008.

By: Amare Mitiku

 Cont....
44

obsno region year popn unemp invst

1 3 1990 18m 5.3 2.5

1 3 2000 24m 15.7 3.12
1 3 2008 30m 24.9 3.79
..... ..... ..... ...... ..... ....
49 1 1990 2m 5.3 2.5
49 1 2000 4m 12.7 4.12
49 1 2008 5m 10.9 6.79
50 4 1990 20m 6.8 3.56
50 4 2000 27m 19.25 4.32
50 4 2008 35m 27.4 5.13
By: Amare Mitiku
 Chapter Two
THE CLASSICAL REGRESSION
45
ANALYSIS
[ The Simple Linear Regression Model]
Economic theories are mainly concerned with the relationships among
various economic variables.
These relationships, when phrased in mathematical terms, can predict
the effect of one variable on another.
The functional relationships of these variables define the dependence
of one variable upon the other variable (s) in the specific form.
The specific functional forms may be linear, quadratic, logarithmic,
exponential, hyperbolic, or any other form.
In this chapter we shall consider a simple linear regression model, i.e.
A relationship between two variables related in a linear form.
We shall first discuss two important forms of relation: stochastic and
non-stochastic, among which we shall be using the former in
econometric analysis.
By: Amare Mitiku
 2.1. Stochastic and Non-stochastic Relationships
46
 A relationship between X and Y, characterized as Y = f(X) is said to be

deterministic or non-stochastic if for each value of the independent variable

(X) there is one and only one corresponding value of dependent variable (Y).
 On the other hand, a relationship between X and Y is said to be stochastic if

for a particular value of X there is a whole probabilistic distribution of values

of Y.
 In such a case, for any given value of X, the dependent variable Y assumes

some specific value only with some probability. Let’s illustrate the
distinction between stochastic and non stochastic relationships with the help
of a supply function.

By: Amare Mitiku

 Cont...
47
 Assuming that the supply for a certain commodity depends on its price

(other determinants taken to be constant) and the function being linear,

the relationship can be put as:
Q=f(P)= α+βP
 The above relationship between P and Q is such that for a particular

value of P, there is only one corresponding value of Q.

 This is, therefore, a deterministic (non-stochastic) relationship since for

each price there is always only one corresponding quantity supplied.

 This implies that all the variation in Y is due solely to changes in X, and

that there are no other factors affecting the dependent variable.

By: Amare Mitiku
 Cont....
48
 If this were true all the points of price-quantity pairs, if plotted

on a two dimensional plane, would fall on a straight line.

 However, if we gather observations on the quantity actually

supplied in the market at various prices and we plot them on a

diagram we see that they do not fall on a straight line.
 Scatter Diagram Q 
 
 
P

By: Amare Mitiku

 Cont...
49

 The deviation of the observation from the line may be attributed to

several factors.
 a. Omission of variables from the function
 b. Random behaviour of human beings
 c. Imperfect specification of the mathematical form of the model
 d. Error of aggregation
 e. Error of measurement

By: Amare Mitiku

 Cont....
50

 In order to take into account the above sources of errors we

introduce in econometric functions a random variable which is

usually denoted by the letter ‘u’ or ‘ε ’ and is called error term
or random disturbance or stochastic term of the function, so
called because u is supposed to ‘disturb’ the exact linear
relationship which is assumed to exist between X and Y.
 By introducing this random variable in the function, the model

is rendered as stochastic of the form:

 Yi = α+βx+ui………………………………………….(2)
By: Amare Mitiku
 Cont....
51

 Thus, a stochastic model is a model in which the dependent

variable is not only determined by the explanatory variable(s)

included in the model but also by others which are not included
in the model.

By: Amare Mitiku

 2.2. Simple Linear Regression model
52

 The above stochastic relationship (2.2) with one explanatory variable

is called simple linear regression model.

 The true relationship which connects the variables involved is split

into two parts: a part represented by a line and a part represented by

the random term ‘u’.

By: Amare Mitiku

 Cont...
53

 The scatter of observations represents the true relationship between Y

and X.
 The line represents the exact part of the relationship and the deviation

of the observation from the line represents the random component of

the relationship.
 Had not the errors been there in the model, we would observe all the

points on the lineẎ1,Ẏ2 ,....Ẏn corresponding to X1 , X 2,...., X n.

 However because of the random disturbance, we

observeY1 ,Y2 ,......,Yn corresponding to By:
XAmare
1 , X Mitiku
2 ,...., Xn.
 Cont....
54

Yi =α+βXi+Ui

Dep Variable the regression line Random Varable

 These points diverge from the regression line by u1 ,u2 ,....,u n.

 The first component in the bracket is the part of Y explained by

the changes in X and the second is the part of Y not explained by

X, that is to say the change in Y is due to the random influence of
ui.

By: Amare Mitiku

 2.2.1 Assumptions of the Classical Linear Stochastic Regression Model
55

 The classicals made important assumption in their analysis of regression .

 The most important of these assumptions are discussed below.

 1. The model is linear in parameters.

 The classicals assumed that the model should be linear in the parameters

regardless of whether the explanatory and the dependent variables are

linear or not.
 This is because if the parameters are non-linear, it is difficult to estimate

them since their value is not known but you are given with the data of the
dependent and independent variables.
By: Amare Mitiku
 Cont...
56

 Example 1. Y = α+ βx + u is linear in both parameters and the

variables, so it Satisfies the assumption.

 Example 2. lnY = α + βlnX + u is linear only in the parameters.

Since the classicals worry on the parameters, the model
satisfies the assumption.
 Check yourself whether the following models satisfy the above
assumption and give your answer.
 a. Y2 =α + βX2 +U
 b. Square Roots of the explainer linear equation
 C. Y= α1/2 + β2X +U

By: Amare Mitiku

 Cont...
57

 2. Ui is a random real variable

 This means that the value which u may assume in any one Period depends on

chance; it may be positive, negative or zero.

 Every value has a certain probability of being assumed by u in any particular

instance.
 2.The mean value of the random variable(U) in any particular period is zero.

 This means that for each value of x, the random variable(u) may assume various

values, some greater than zero and some smaller than zero, but if we considered
all the positive and negative values of u, for any given value of X, they would
have an average value equal to zero. In other words, the positive and negative
By: Amare Mitiku
values of u cancel each other.
 Cont...
58
 Mathematically, E(Ui)=0

 3.The variance of the random variable(U) is constant in each period

(the assumption of homoscedasticity).

 For all values of X, the u’s will show the same dispersion around their

mean.
 In the ff. Fig. this assumption is denoted by the fact that the values that

u can assume lie with in the same limits, irrespective of the values of X.

 For X1 , u can assume any value with in the range AB; for X 2 , u can

assume any value with in the range CD which is equal to AB and so on.
By: Amare Mitiku
 Cont...
59
 Graphically;
 Y
E(Y)=α+Βx

HomoscedasticVariance X
 Mathematically;
 Var (Ui) = E[Ui- E(Ui)]2 = E (Ui)2 = σ2, (Since E(Ui) = 0).
 This constant variance is called homoscedasticity assumption and the constant variance itself

is called homoscedastic variance .

By: Amare Mitiku

 4. The random variable (U) has a normal distribution
60

 This means that the values of the random variable u (for each x) have a bell

shaped symmetrical distribution about their zero mean and constant

variance σ2, i.e.

Ui∼N(0,σ2) ………………………………………..……2.4

5. The random terms of different observations (U , U ) , are independent

i j

(The assumption of no autocorrelation)

 This means the value which the random term assumed in one period does

not depend on the value which it assumed in any other period.

Algebraically, Cov(Ui, Uj) = E[Ui-E(Ui)][Uj-E(Uj)] ……………..….2.5
By: Amare Mitiku E(UiUj) =0
 Cont...
61

6. The Xi are a set of fixed values in the hypothetical process of repeated

sampling which underlies the linear regression model.

This means that, in taking large number of samples on Y and X, the X i

values are the same in all samples, but the u i values differ from sample

to sample, and so do the values of Yi .

7. The random variable (U) is independent of the explanatory variables.

 This means that there is no correlation between the random variable and the explanatory variables.

 If two variables are unrelated their covariance is zero.

 Hence, Cov(Xi, Ui) = 0

 Proof: Cov(Xi, Ui) = E[[Xi-E(Xi)][Ui-E(Ui)]]...................……………………………..….(2.6)

 Cov(Xi, Ui) = E[Xi-E(Xi)][Ui)] Since E(Ui)=0

By: Amare Mitiku
 Cont....
62

 Cov(XiUi) = E(XiUi)-E(Xi)E(Ui)

= E(XiUi)

= XiE(Ui), Since Xi is fixed.

=0

8. The explanatory variables are measured without error

U absorbs the influence of omitted variables and possible errors of measurement in the Y’s. i.e., we

will assume that the regressors are error free, while Y values may or may not include errors of

measurement.
By: Amare Mitiku
 Cont...
63
 We can now use the above assumptions to derive the following basic concepts.
 A. The dependent variable Yi is normally distributed.
 i.e Yi~N[(α+βXi,σ2)]………………………………(2.7)
 Proof
 Mean: Ε (Yi)=E(α+βXi +ui)
• = E(α+βXi) since, E(Ui)=0
• = α+βXi
 Variance
• Var(Yi)=E(Yi-E(Yi))2
• =E(α+βXi +ui- E(α+βXi))2
• =E(Ui)2
• Var(Yi)=σ2. …………………………….........…….(2.8)
 The shape of the distribution of Yi is determined by the shape of the distribution of
Ui which is normal by assumption 4.
 Since α and β, being constants, they don’t affect the distribution of Yi.
 Furthermore, the values of the explanatory variable, Xi , are a set of fixed values by
assumption
By: Amare Mitiku5 and therefore, don’t affect the shape of the distribution of Yi. :.Yi~N[(α+βXi,σ2)]
 Cont....
64
 B. successive values of the dependent variables are
independent,
 i.e. Cov(Yi,Yj)=0
Proof:
 Cov(Yi, Yj) = E[[Yi-E(Yi)][Yj-E(Yj)]]...................……………………………..….(2.6)

 = E[(α+βXi +ui- E(α+βXi +ui)][α+βXj +Uj-E(α+βXj +uj)]

 Since, Yi=α+βXi +ui and Yj=α+βXj +Uj

 = E(α+βXi +ui-α-βXi)(α+βXj +Uj-α-βXj ) Since, E(Ui)2=0

 =
E(UiUj)=0 from Equation 2.5

 Therefore, E(YiYj)=0

By: Amare Mitiku

 2.2.2 Methods of estimation –rEgular??
65

Specifying the model and stating its underlying assumptions are the first stage of any

econometric application.

The next step is the estimation of the numerical values of the parameters of economic

relationships.

The parameters of the simple linear regression model can be estimated by various methods.

Three of the most commonly used methods are:

1. Ordinary least square method (OLS)

2. Maximum likelihood method (MLM)

3. Method of moments (MM)

 But, here we will deal with the OLS methods of estimation.

By: Amare Mitiku

 2.2.2.1 The ordinary least square (OLS) method

66
 The model Yi=α+βXi +Ui is called the true relationship between Y and X because Y

and X represent their respective population value, and α and β are called the true
parameters since they are estimated from the population value of Y and X.
 But it is difficult to obtain the population value of Y and X because of technical or

economic reasons.
 So we are forced to take the sample value of Y and X. The parameters estimated

from the sample value of Y and X are called the estimators of the true parameters α
and β and are symbolized as α and β hats.

 The model Yi=ᾰ+βXi +êi , is called estimated relationship between Y and X since α

and β hats are estimated from the sample of Y and X and ei represents the sample

counterpart of the population random disturbance Ui.

By: Amare Mitiku
 Cont...
67

 Estimation of α and β by least square method (OLS) or classical least square (CLS) involves

finding values for the estimates α and β hats which will minimize the sum of square of the squared

residuals (∑ei2).

 From the estimated relationship Yi=α+βXi +ei ,(hats of parameters) , we obtain:

• ei=Yi-α-βXi.............................................................2.6

• ∑ei2 =∑(Yi−α-βXi )2………........……………….(2.7)

To find the values of α and β that minimize this sum, we have to partially differentiate ∑e i 2

with respect to α and β hats and set the partial derivatives equal to zero.

By: Amare Mitiku

 Minimisation of Error Sum Square

68
Errors are given ei  Yi  a   xi . Some of them are
by
positive and some others are negative. Since mean of these
errors is zero, E  e   0 , it is customary to take sum of
 i
 
squared errors and estimate the unknown parameters a and
 that minimise the sum squared errors.
2
S   ei2   
Y  a   x 
i i
 (1)
 
i i
Sign of each and every squared error would be posit ive
 e2   0
 
when e ~ N  2
 0,

 .



 i  i  

S   e2 ~  n
2 distribut ion where subscript n stands for
i i
degrees of freedom which equals the number of terms in S

Normal equations of the least square estimator are obtained

by minimising S function (1) with respect to a and  .
 Derivation of Normal Equations

69
S  2 Y  a   x 1  0 and
a   i i 
S  2 Y  a   x   x   0
   i i  i 

Thus normal equations are

 yi  Na    xi (2)
i i
 xi yi  a  xi    xi2 (3)
i i i
This is a system of two equations, (2) and (3) , and two unknowns
a and  . All other values such as  xi ,
 xt yt ,  xt2 ,  y t and N are known from the sample
information on X and Y. In order to get value of  eliminate a
by multiplying the (2) by  x and (3) by N and take a difference
i
of the resulting two equations.
 OLS Estimators

70

 
2
 xi  yi  Na  xi    x 
 i 
(4)
i i i  i 

N  x y  a N  x   N  x2 (5)
i i i i i i i
Now subtracting (5) from (4) we get the estimator for
.
N x y  x  y
ˆ i i i i ii i
  (6)
 
2
N  x 2    x 
i i  i i 
Estimator for a can be found by dividing both sides
of (2) by N and using the average values x and y .
a  y  ̂ x (7)
 An Example of OLS Estimation
71
Food expenditure and income: data and prediction
Y X XY X2 Y2 Ypred Sqpredy prede sqprede
4 5 20 25 16 2.866285 8.21559 1.133715 1.28531
6 8 48 64 36 5.742472 32.97598 0.257528 0.066321
7 10 70 100 49 7.65993 58.67453 -0.65993 0.435508
8 12 96 144 64 9.577388 91.72636 -1.57739 2.488153
11 14 154 196 121 11.49485 132.1315 -0.49485 0.244873
15 17 255 289 225 14.37103 206.5266 0.628967 0.395599
18 20 360 400 324 17.24722 297.4666 0.75278 0.566678
22 25 550 625 484 22.04087 485.7997 -0.04087 0.00167
Sumy Sumx Sumxy sumxsq sumysq 36.4218 Smsqpredy smsqprede
91 111 1553 1843 1319 127.4218 1313.517 -3.9E-05 5.484111
 Estimates
72
N  xi yi   xi  yi
ˆ  i i i
2
 
N  xi2    xi 
i  i 

Or using the values from the above table.

8(1553)  111 (91) 12424  10101 2323

ˆ     0.95873 (8)
8(1843)  (111 ) 2 14744  12321 2423

91 111
a  y  ˆ x   0.95872  11 .375  0.95872(13.875)  11 .375  13.30224  1.927
8 8
(9)

The fitted regression line is

yˆ i  ˆ1  ˆ 2 xi  1.92724  0.95873 xi (10)

 Interpretation and Prediction

73
Both slops and intercepts make economic sense. In this sample expenditure
on foods is determined by weekly income of an individual, people spend
95.9% percent of their weekly income in food expenditure. People who do
not have any income receive an income subsidy of 1.93 per week.
 Mean prediction

We can use equation (10) to find the predicted values Ŷi for each

observation on x i . These are reported as YPRED in the above tab le. If the
weekly income is 40 predicted foo d expenditure will be 36.422. Error terms
are also estimated using the fact that

ˆ  y  y
e ˆ x  y 1.92724  0.95873x
ˆ  y a
i i i i i i i
These predicted errors are reported as prede in the above table. Note that as
expected some of the errors are negative and some other are positive.
 74
2.2.2.2 Estimation of a function with zero intercept

 Suppose it is desired to fit the line Yi= α+βXi+Ui, subject to the

restriction α=0.
 To estimate ˆβ , the problem is put in a form of restricted
minimization problem and then Lagrange method is applied.
 We minimize: ∑ei2 =Σ(Yi-ά- βXi)2= where i runs from 1....n.
Subject to: α=0
 The composite function then becomes Z=Σ(Yi-ά- βXi)2–λα where λ
is a Lagrange multiplier.
 We minimize the function with respect to ά, β and λ.
 Zά=-2Σ(Yi-ά- βXi)–λ=0 ....................................a
 Zβ= -2Σ(Yi-ά- βXi)(Xi)=0...................................b
 Zλ= - ά=0.............................................................c
By: Amare Mitiku
 Cont....
75
 Substituting (c) in (b) and rearranging we obtain:

 ΣXi(Yi−βXi)=0

 ΣXiYi-βΣXi2=0

 Β=ΣXiY2 i
ΣXi

This formula involves the actual values (observations) of the variables and not

their deviation forms

By: Amare Mitiku

 2.2.2.3. Statistical Properties of Least Square Estimators

76
There are various econometric methods with which we may obtain the estimates of
the parameters of economic relationships.
We would like to have an estimated parameters which is/are as close as the value of
the true population parameters i.e. to vary within only a small range around the true
parameter.
How are we to choose among the different econometric methods, the one that gives
‘good’ estimates? We need some criteria for judging the ‘goodness’ of an estimate.
‘Closeness’ of the estimate to the population parameter is measured by the mean and
variance or standard deviation of the sampling distribution of the estimates of the
different econometric methods.
We assume the usual process of repeated sampling i.e. we assume that we get a very
large number of samples each of size ‘n’; we compute the estimates β’s from each
sample, and for each econometric method and we form their distribution.
We next compare the mean (expected value) and the variances of these distributions
and we choose among the alternative estimates the one whose distribution is
concentrated as close as possible around the population parameter.
By: Amare Mitiku
 PROPERTIES OF OLS ESTIMATORS
77

 The ideal or optimum properties that the OLS estimates possess may

be summarized by well known theorem known as the Gauss-Markov

Theorem.
 Statement of the theorem:“Given the assumptions of the classical

linear regression model, the OLS estimators, in the class of linear

and unbiased estimators, have the minimum variance, i.e. the OLS
estimators are BLUE.

By: Amare Mitiku

 Cont...
78

 According to the this theorem, under the basic assumptions of the classical

linear regression model, the least square estimators are linear, unbiased and

have minimum variance (i.e. are best of all linear unbiased estimators).

 Some times the theorem referred as the BLUE theorem i.e. Best, Linear,

Unbiased Estimator.

 An estimator is called BLUE if:

a. Linear: a linear function of the a random variable, such as, the dependent
variable Y.
b. Unbiased: its average or expected value is equal to the true population
parameter.
c. Minimum variance: It has a minimum variance in the class of linear and
unbiased estimators. An unbiased estimator with the least variance is known as
an
By: Amare efficient estimator.
Mitiku
 Cont...
79

 According to the Gauss-Markov theorem, the OLS estimators

possess all the BLUE properties.

 The detailed proof of these properties are presented below.
• A. Linearity : for β hat
• Proposition: ά and β hats are linear in Y.

• Proof: from the OLS estimators of β hat:

By: Amare Mitiku

 Econometrics Assignment
80

 Assume you are given a ten year investment expenditure and

interest rate data as follows:
Year Investment in million birr Interest in %

1998 65 5
1999 80 4.5
2000 83 4.5
2001 76 5.5
2002 77 6
2003 71 6
2004 75 6
2005 74 5
2006 69 7
2007 78 6.5
By: Amare Mitiku
 Cont…
81
Then,
Based up on the economic apriori criterion
 1.Specify the simple linear regression model
With zero intercept ?
With non zero intercept?
 2. Estimate the values of the parameters ?
By what amount will investment demand increase if interest declines
by 1%?
What will be the level of investment if rate of interest is 10%?
 3. Calculate the sample error sum of squares?
 4. Estimate the variance of the intercept?

 5. Estimate the variance of the intercept?

For the zero intercept model?
For non-zero intercept model?

By: Amare Mitiku

 Cont…
82
 6. Calculate the corresponding standard errors of the intercept
and the slope estimators?
 7. Calculate the correlation coefficient and coefficient of

Determination?
8. Interpret the values of R2?
9. Test whether the estimated values of the parameters are
significant or not using
 Standard Error test?

 Student-test? Given LS=5%=2.10 for two tail and 3.63 for one tail.
 Confidence Interval? At ls=5%=1.96 for two tail test.

 Acct MSC 2008 Reg &Ext.

 Deadline: 29/05/2008E.C.
 27/05/08 for Reg

By: Amare Mitiku

 83

By: Amare Mitiku

 84

By: Amare Mitiku

 85

By: Amare Mitiku

 86

By: Amare Mitiku

 87

By: Amare Mitiku

 88

By: Amare Mitiku

 89

By: Amare Mitiku

 90

By: Amare Mitiku

 91

By: Amare Mitiku

 92

By: Amare Mitiku

 93

By: Amare Mitiku