Scribd
Upload
33 views

The Nature of Econometrics and Economic Data

Econometrics uses statistical methods to analyze economic data and test economic theories. It focuses on problems with non-experimental economic data collected from individuals, firms or economies. The steps in empirical analysis involve identifying an economic problem, forming a hypothesis based on theory, collecting data, and using that data to reject or verify the hypothesis. Economic data can be cross-sectional, time series, pooled cross sections or panel data. Causality is difficult to determine as correlations do not necessarily imply causation and other factors must be held equal, known as ceteris paribus, for isolating the effect of one variable.

Uploaded by

dude
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
33 views

The Nature of Econometrics and Economic Data

Econometrics uses statistical methods to analyze economic data and test economic theories. It focuses on problems with non-experimental economic data collected from individuals, firms or economies. The steps in empirical analysis involve identifying an economic problem, forming a hypothesis based on theory, collecting data, and using that data to reject or verify the hypothesis. Economic data can be cross-sectional, time series, pooled cross sections or panel data. Causality is difficult to determine as correlations do not necessarily imply causation and other factors must be held equal, known as ceteris paribus, for isolating the effect of one variable.

Uploaded by

dude
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 23

The Nature of Econometrics

and Economic Data

1
Outline
What is Econometrics?

Steps in Empirical Economic Analysis

The Structure of Economic Data

Causality and The Notion of Ceteris Paribus

2
What is Econometrics?
Econometrics is based upon the development of
statistical methods for

 estimating economic relationships,

 testing economic theories,

 evaluating and implementing government and business


policy.

3
What is Econometrics?
The most common application of econometrics?

 Forecasting of such important macroeconomic


variables such as

Interest rates,

Inflation rates,

Gross domestic product. and so on.

4
What is Econometrics?
Focuses of Econometrics is on the problems inherent
in collecting and analyzing non experimental
economic data.

Experimental data?
 Data which are accumulated through controlled
experiments.

Controlled Experiments?
 A controlled experiment is one in which everything is
held constant except for variables being examined.

5
What is Econometrics?
Example for Controlled Experiments?
 Separating biological subjects into two groups, an
experimental group and a control group.
 No treatment is given to the control group, while
the experimental group is changed according to
some key variable of interest, and the two groups
are otherwise kept under the same conditions.

Non experimental data ?


 data which are not accumulated through controlled
experiments on individuals, firms, or segments of
the economy.
6
Steps in Empirical Economic Analysis

Problem Economic theory Hypothesis

Empirical analysis Data Reject/verify

Sample Population

7
7
Steps in Empirical Economic Analysis

𝑌 = 𝛽0 + 𝛽1 𝑋 + 𝑢 Population Parameters

𝑌 = 𝛽0 + 𝛽1 𝑋 + 𝑢 Sample Estimates
The Structure of Economic Data
Cross-Sectional Data

Time Series Data

Pooled Cross Sections

Panel Data

9
Cross-Sectional Data
Cross-Sectional data set?
 A sample of individuals, households, firms, cities,
states, countries, or a variety of other units, taken at a
given point in time.

Important features?
 Random Sample?
 A random sample is a subset of a statistical
population in which each member of the subset has
an equal probability of being chosen.

 Ordering of the data does not matter for econometric


analysis
10
Cross-Sectional Data
Sometimes random sampling is not appropriate
assumption. Can you bring an example for this?

 Studying factors affect the accumulation of family


wealth

 Maybe wealthier families are less likely to disclose


their wealth! So resulting sample is not random sample.

11
Time Series Data
Time series data set?
 Set of observations on a variable or several variables
over time.

Examples?
 Stock prices
 Money supply
 Consumer Price Index
 Gross Domestic Product

12
Time Series Data
Important Features?
 Time is an important dimension in a time series data;
because past events can influence future events. So
ordering of observations conveys important
information.

 Economic observations can rarely, if ever, be assumed


to be independent across time. For example, knowing
something about the GDP from last quarter tells us
quite a bit about likely range of GDP during this
quarter.

13
Time Series Data

 Another feature of time series data is the data


frequency at which the data are collected.

 Many weekly, monthly, and quarterly economic


time series display a strong seasonal pattern.
Example?
 Monthly data on housing starts differs across the
months simply due to changing weather conditions.

14
Pooled Cross Sections
Pooled Cross Sections?
 Data sets which have both cross-sectional and time
series features.
Example?
 Suppose two cross-sectional household surveys are
taken, one in 1985 and one in 1990.

 In order to increase our sample size, we can form a


pooled cross section by combining the two years.

 Because random samples are taken in each year, it


would be a fluke if the same household appeared in the
sample during both years.
15
Pooled Cross Sections
Pooling cross sections from different years is often
an effective way of analyzing the effects of a new
government policy.

A pooled cross section is analyzed much like a


standard cross section, except that we often need
to see how a key relationship has changed over
time.

16
Panel Data
Panel data set?

 A panel data set consists of a time series for each cross-


sectional member in the data set.

Difference between panel data and pooled cross


section?

 In panel data, the same cross-sectional units


(individuals, firms, ….) are followed over a given time
period.
17
Causality and
The Notion of Ceteris Paribus
What does the notion of ceteris paribus mean?

 It means that other (relevant) factors being equal.

The most economic questions are ceteris paribus


by nature. Can you bring an example?

 In analyzing consumer demand, we are interested


in knowing the effect of changing the price of a
good on its quantity demanded, while holding all
other factors fixed.
18
Causality and
The Notion of Ceteris Paribus
If other factors are not held fixed, then we cannot
know the causal effect between variables.

The key question in most empirical studies:

Have enough other factors been held fixed to make a


case for causality?

19
Causality and
The Notion of Ceteris Paribus
Example:
 By how much will wage increase, if a person give
another year of education?

 Implicit assumption: all other factors that influence


wages such as experience, family background,
intelligence etc. are held fixed.

 Experiment: Choose a group of people, randomly


give each person an amount of education
(infeasable!), and then measure their wages.

20
Causality and
The Notion of Ceteris Paribus
Does correlation imply causation?

 Empirically observed linear correlation is


neither a necessary nor a sufficient condition
for causality.

 Correlation is not causation but it sure is a hint.

 Example?

21
Causality and
The Notion of Ceteris Paribus
Example:

 As ice cream sales increase, the rate of drowning


deaths increases sharply.

 Therefore, ice cream consumption causes


drowning. Is it true?

 There is a confounding variable which is simply a


hidden third variable that affects both causes of the
correlation: TEMPRATURE.

22
Causality and
The Notion of Ceteris Paribus
Example:

 When a country's debt rises above 90% of GDP,


growth slows.

 Therefore, high debt causes slow growth. Is it true?

 This argument by Carmen Reinhart and Kenneth


Rogoff was refuted by Paul Krugman: in actuality,
low growth causes debt to increase.

23

You might also like