Submitted by: Submitted by nzcarol
Views: 343
Words: 7938
Pages: 32
Category: Business and Industry
Date Submitted: 08/16/2012 03:48 AM
Short Course in Econometrics
P M Dawson
INTRODUCTION
THE NATURE OF ECONOMETRICS AND THE MODELLING PROCESS
What is Econometrics?
Econometrics is the branch of economics which links economic theory with economic
data with a view to making economic decisions. In particular we are interested in the
amount of change needed for a policy instrument to bring about the desired effect.
For example, what is the impact of increasing the tax, and therefore the price, on
cigarettes, alcohol and petrol (i.e. is the demand for these products relatively elastic or
inelastic)? What causes stock market fluctuations? What determines the price of
houses, or the wage paid to workers? What are the determinants of money demand
and money supply?
The Modelling Process
There are several stages involved in the modelling process:
1.
2.
3.
4.
5.
6.
7.
Statement of theory or hypothesis
Specification of the mathematical model
Specification of the econometric model
Obtaining the data
Estimation of the econometric model and diagnostic testing
Hypothesis testing
Prediction (or forecasting)
Example: The Relationship Between Income and Consumption
Using the simple Keynesian consumption function as an example to explain each of
these 7 stages.
Stage 1 - Statement of theory or hypothesis
Economic theory states that consumer expenditure is dependent upon income. There
are a number of issues raised here from economic theory:
•
the direction of causation is that income determines consumer expenditure
1
•
•
consumer expenditure is a positive function of income (an increase in income will
lead to an increase in consumer expenditure)
the marginal propensity to consume (MPC), which is the proportion of any
increase in income which is spent on consumption, must lie between 0 and 1.
Stage 2 - Specification of the mathematical model of the theory
Formulation of a simple mathematical function for the consumption function could be
C = f (Y )
(1)...