Applied Econometrics 3rd

edition
INTRODUCTION

1. What is Econometrics?
2. The Stages of Econometric Work

From the desk of Ms Imrana Bano 1

 Applied Econometrics 3rd
edition
What is Econometrics?
Econometrics means measurement (metrics in greek) in economics.
The importance of applied work in economics is increasing constantly.
Theory suggests that X affects Y but is this true or not?
This is the work of the applied econometrician.

From the desk of Ms Imrana Bano 2

 Applied Econometrics 3rd
edition
What is Econometrics?
◦ Examples of problems that may be tackled by an Econometrician
(a) Modelling long-term relationships among prices and interest rates.
(b) Examining the effect of inflation in unemployment rates
(c) Examining the effect of disposable income on consumption

From the desk of Ms Imrana Bano 3

 Applied Econometrics 3rd
edition
What is Econometrics?
◦ Examples of problems that may be tackled by an Econometrician (continued)
(a) Determining the factors that affect GDP per capita growth
(b) Testing the validity of the CAPM and APT theories
(c) Forecasting the correlation among the returns and the stock indices of two countries.

From the desk of Ms Imrana Bano 4

Applied Econometrics 3rd
edition
The Stages of Applied
Econometric Analysis
Economic Theory

Econometric Model Data

Model Estimation

Specification Testing and Diagnostics

Is the Model Adequate?

No Yes

Test any hypothesis

Use for Predictions and Policy Making

From the desk of Ms Imrana Bano 5
 Applied Econometrics 3rd
edition
The Structure of Economic Data
◦ There are three different types of economic data

◦ TIME SERIES
◦ CROSS SECTIONAL
◦ PANEL DATA

From the desk of Ms Imrana Bano 6

 Applied Econometrics 3rd
edition
The Structure of Economic Data
◦ Time Series Data
◦ Examples: GDP, Unemployment, Inflation, Stock Prices, etc
◦ Vectors or Columns (like in a spreadsheet)
◦ Frequencies: Yearly, Bi-annually, Quarterly, Monthly, Weekly, Daily, Hourly.
◦ Lots of different values for different time periods for one country, state, city, market.

From the desk of Ms Imrana Bano 7

 Applied Econometrics 3rd
edition
The Structure of Economic Data
◦ Cross-Sectional Data
◦ Examples: GDP, Unemployment, Inflation, Stock Prices, etc.
◦ Vectors or Rows (like in a spreadsheet)
◦ Frequencies: Yearly, Bi-annually, Quarterly, Monthly, Weekly, Daily, Hourly.
◦ Lots of different values for different countries, states, cities, markets, but for one time
period only.

From the desk of Ms Imrana Bano 8

 Applied Econometrics 3rd
edition
The Structure of Economic Data
◦ Panel Data
◦ A combination of time series and cross-sectional data.
◦ Examples: GDP, Unemployment, Inflation, Stock Prices, etc.
◦ Matrices (columns and rows to make an n times m matrix)
◦ Frequencies: Yearly, Bi-annually, Quarterly, Monthly,
Weekly, Daily, Hourly.
◦ Lots of different values for different countries, states, cities,
markets, and for different time periods.

From the desk of Ms Imrana Bano 9

 Applied Econometrics 3rd
edition
The Structure of Economic
Data - Notation
◦ Time series: Yt, t=1990, 1991, …, 2012
◦ Cross-Sectional: Yi, i=1, 2, 3, …, 40
◦ Panel Data: Yit, i and t defined as above.

◦ It is common to denote each observation by the letter t and the total number of
observations by T for time series data, and to denote each observation by the letter i
and the total number of observations by N for cross-sectional data.

From the desk of Ms Imrana Bano 10

 Applied Econometrics 3rd
edition
The Structure of Economic
Data – Quantitative vs Qualitative
◦ The data may be quantitative and qualitative.

◦ Quantitative (e.g. GDP per capita, exchange rates, stock prices, unemployment rates)

◦ Qualitative (e.g. Day of the week, gender, level of education)

From the desk of Ms Imrana Bano 11

 Applied Econometrics 3rd
edition
Basic Data Handling

◦ Looking at raw data

◦ Graphical Analysis
◦ Summary Statistics
◦ Components of a Time Series
◦ Indices and Base Dates
◦ Data Transformations

From the desk of Ms Imrana Bano 12

 Applied Econometrics 3rd
edition
Basic Data Handling - Looking at raw data
◦ Before getting into the statistical and econometric tools, a preliminary analysis is
extremely important
◦ “Get the feel” of your data
◦ Look at the numbers on a spreadsheet. Note number of series/end and start dates, range
of values etc.
◦ Outliers, discontinuities, structural breaks etc.

From the desk of Ms Imrana Bano 13

 Applied Econometrics 3rd
edition
Basic Data Handling – Graphical Analysis
◦ Graphs facilitate the inspection process
◦ See the “big picture”
◦ Histograms: give an indication of the distribution of a variable
◦ Scatter plots: give combinations of values from two series for the purpose of determining their
relationship (if any)
◦ Line Graphs: facilitate the comparisons of series
◦ Bar Charts: good for comparisons
◦ Pie Charts: good for percentages/portions

From the desk of Ms Imrana Bano 14

 Applied Econometrics 3rd
edition
Basic Data Handling – Graphical Analysis
• Histograms: give an indication of the distribution of a variable
• Command in Eviews (View\Histogram and Stats)

From the desk of Ms Imrana Bano 15

 Applied Econometrics 3rd
edition
Basic Data Handling – Summary Statistics
• Scatter Plots: give combinations of values from
two series for the purpose of determining their
relationship (if any)

◦ Eviews command (open the

two series together in a group
and choose
View/Graph/Scatter)

From the desk of Ms Imrana Bano 16

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Line Graphs: facilitate
the comparisons of series

Command in Eviews:
Plot X Y

From the desk of Ms Imrana Bano 17

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Bar Charts: facilitate
the comparisons of
series

Command in Eviews:
View/Graph/Bar

From the desk of Ms Imrana Bano 18

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Pie Charts: Good for
proportions

Command in Eviews:
View/Graph/Pie

From the desk of Ms Imrana Bano 19

 Applied Econometrics 3rd
edition
Basic Data Handling – Summary Statistics
• Summary statistics provide a more precise idea of the distribution
of a variable (mean, variance, st. dev. etc)
• For comparisons open the variables in a group.

From the desk of Ms Imrana Bano 20

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
An economic or financial time series consists of up to four
components
1. Trend (smooth, long-term/consistent upward or downward
movement)
2. Cycle (rise and fall over periods longer than a year)
3. Seasonal (within year pattern seen in frequency data)
4. Irregular (random component, episodic – unpredictable but
identifiable – and residual – unpredictable and unidentifiable)

From the desk of Ms Imrana Bano 21

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
An economic or financial time series consists of up to four components

From the desk of Ms Imrana Bano 22

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Seasonal (within year pattern seen in quarterly, monthly or weekly data)

From the desk of Ms Imrana Bano 23

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Trend (smooth, long-term/consistent upward or downward movement)

From the desk of Ms Imrana Bano 24

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Cycle (rise and fall over periods longer than a year)

From the desk of Ms Imrana Bano 25

 Applied Econometrics 3rd
edition
Basic Data Handling–Components of a Time Series
Irregular (random component, episodic – unpredictable but
identifiable – and residual – unpredictable and unidentifiable)

From the desk of Ms Imrana Bano 26

 Applied Econometrics 3rd
edition
Basic Data Handling – Indices and Base Dates
◦ Splicing two indices and change the base date

218 is 100
258 is X?
X=100*(258/218) or X=258*(100/218) or X=258/2.81

From the desk of Ms Imrana Bano 27

 Applied Econometrics 3rd
edition
Basic Data Handling – Data Transformations
◦ Nominal vs Real data (use appropriate price deflator)

From the desk of Ms Imrana Bano 28

 Applied Econometrics 3rd
edition
Basic Data Handling – Data Transformations
◦ Natural Logs (ln) have three advantages:

1. Natural logs linearize the exponential trends in the

series (makes the graph look smoother).
2. Natural logs linearize a model that is non linear in
parameters (consider Cobb-Douglas Production
function).
3. The OLS coefficients are elasticities.
From the desk of Ms Imrana Bano 29
 Applied Econometrics 3rd
edition
Basic Data Handling – Data Transformations
◦ Differencing
In case we want to remove the trend component from a
time series entirely (i.e. in order to make it stationary)

First differences:
ΔYt = Yt – Yt-1
Second diffferences:
Δ2Yt = Δ(Yt – Yt-1) = ΔYt – ΔYt-1 =
= (Yt – Yt-1) – (Yt-1 – Yt-2) = Yt – 2Yt-1+ Yt-2
From the desk of Ms Imrana Bano 30
 Applied Econometrics 3rd
edition
Basic Data Handling – Data Transformations
◦ Growth rates

Discretely compounded
growth rate of Yt =(Yt-Yt-1)/Yt-1

Continuously compounded
growth rate of Yt = ln(Yt-Yt-1) = ln(Yt)-ln(Yt-1)

From the desk of Ms Imrana Bano 31