You are on page 1of 26

Econometrics for Management

(MGMT3071)

Teklebirhan Alemnew (Assistant Professor)


tbalemnew@gmail.com
AAU, 2023
Course Contents

Chapter 1 – Introduction

Chapter 2 - Regression Analysis

Chapter 3 - Regression analysis: Further details

Chapter 4 - Binary dependent variable

Chapter 5 - Time series Analysis

By: Teklebirhan A. 2
Assessment
.

 Quizzes (2) – 20%


 Assignment (2) – 30%
 Final Exam – 50%

By: Teklebirhan A. 3
References
 Gujarati, D., Basic econometrics, 5th ed. 2008.

 Gujarati, D., Econometrics by example, 2011.

 Jeffrey Wooldridge 2009 or 2012, Introductory Econometrics, 4th


or 5th edition, Thomson SouthWestern

By: Teklebirhan A. 4
Chapter One:
Introduction

By: Teklebirhan A. 5
1.1. What is Econometrics and its
Methodology?
What is Econometrics?
 Different theories based on abstract reasoning have been
developed to understand complex phenomena

 Are these theories valid in the real world? (empirical validity?)

 Econometrics is a combination of economic theory, mathematical


economics and statistics, but it is completely distinct from each
one of these three branches of science.

By: Teklebirhan A. 6
Cont…
 Econometrics is based on statistical methods for

• Estimating, quantifying & checking the strength of the


relationship among variables,

• Testing the validity of theories in explaining the real world by


confronting them with real data,

• Evaluating (impact) and implementing government and


business policies.

 The last two points shows that econometrics methods go beyond


testing simple correlations.

By: Teklebirhan A. 7
Cont…
 Why study Econometrics?

 Unlike "hard" sciences, in social sciences, we have no experimental


data / Laboratories.

 The world around us is very complex, we cannot control


everything that happens outside of the question that we want to
study.

 To make statistical inference (draw conclusions for the whole


population) we have to deal with non-experimental data, based on
samples of a population.-- Survey data.

By: Teklebirhan A. 8
Cont…
 Some relevant variables are not always available / observable. This
may cause estimation bias. Econometrics provides solutions to
these problems.

 Three main goals of econometrics


a) Analysis: - Testing Economic Theory – empirical testing
 It aims primarily at the verification/validity of economic theories.
b) Policy-Making
 obtaining numerical estimates of the economic relationships for
decision making.
 E.g, gov’t policy on currency devaluation (Imp/exo elasticity)
By: Teklebirhan A. 9
Cont…
c) Forecasting or Prediction

 Obtaining future values of certain variable

 Enable us to reduce our uncertainty in the future

 It enables policy makers to judge whether it is necessary to take


any measure in order to influence the relevant variables.

 For instance, government’s decision on its current employment


policy may be influenced by forecasted level of employment for
the coming, say, ten years.

By: Teklebirhan A. 10
Cont…
 Succinctly, this means that to formulate current employment
policy the government has to know, (among others):

• What is the current situation of employment?

• What the level of employment will be, say in ten years’ time if
no measure is taken by the government?

 Finally, if the forecasted level of employment is lower than the


acceptable level of employment leading to high level of
unemployment.

 Hence, the government must take measures to reduce


unemployment over time. 11
By: Teklebirhan A.
Cont…

By: Teklebirhan A. 12
Cont…
Methodology of Econometric Analysis
 In any econometric research we may distinguish four stages:

a) Specification of the model

b) Estimation of the model

c) Evaluation of the estimates

d) Use the model for Prediction and Decision Making

By: Teklebirhan A. 13
Cont…
a) Specification of the model

 It means expressing the relationship that we want to estimate in


mathematical form

 This step involves three important tasks:


 Identification of the relevant variables to be included in the model

 Determination of the mathematical form of the model

 Determination of the expected signs and magnitudes of the


parameters of the model

By: Teklebirhan A. 14
 Suppose that you are an econometrician working
for Cottex Textile Industry Plc. As a marketing
policy advisor of the industry, suppose you are
seeking to identify the determinants of the
quantity demanded of the industry’s bed sheet in
Addis Ababa. At this moment suppose also that
you believed that conducting an econometric
research to address this question is the most
efficient way.
quantitatively
measure the
different main
determinants 15
By: Teklebirhan A.
Cont…
 Identification of the relevant variables

 In applied econometrics, there are three basic criteria for


identification of relevant variables to be included in an
econometric analysis. These are:

 Theory,

 Previous studies and

 Intuition.

By: Teklebirhan A. 16
Cont…

By: Teklebirhan A. 17
Cont…

By: Teklebirhan A. 18
Cont…
 The determination of the functional form of the relationship
requires understanding the actual functional relationship (linear,
quadratic, logarithmic, exponential, etc) between the variables.

 In this step it is hard to apply our knowledge of economic theories

 Thus, it is the task of the researcher to use his/her own mental


talent to determine about the mathematical form of the model s/he
is interested on.

 To do this, s/he has to put plausible assumptions regarding the way


that the dependent variable responds to the change in one or more
of the independent variables. By: Teklebirhan A. 19
Cont…

By: Teklebirhan A. 20
Cont…

By: Teklebirhan A. 21
Cont…

By: Teklebirhan A. 22
Cont…

By: Teklebirhan A. 23
Cont…
 Conclusion:

 Specification of the model is the most important and the toughest


stage of any econometric analysis

 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.

By: Teklebirhan A. 24
Cont…
 Some of the common reasons for incorrect specification of the
econometric models are:

 The imperfections, looseness of statements in economic theories.

 The limitation of our knowledge of the factors which are


operative in any particular case.

 The formidable obstacles presented by data requirements in the


estimation of large models.

By: Teklebirhan A. 25
Cont…
 The most common errors of specification are:

 Omissions of some important variables from the function.

 The omissions of some equations (for example, in simultaneous


equations model).

 The mistaken mathematical form of the functions.

By: Teklebirhan A. 26

You might also like