Econ 3334

Welcome to

Econ 3334
Introductory Econometrics

1
Teaching Team Econ 3334

Instructor: Xun (Sean) Lu (陸迅)

Associate Professor, Department of Economics
Specialty: Econometrics

Teaching Assistant: Peter Tsui

2
Lecture and Tutorial Information: Econ 3334

Lecture

Monday and Friday

Webpage: http://canvas.ust.hk

3
Lecture and Tutorial Information: Econ 3334

Tutorial

Not weekly, about 8 tutorials

The first week will NOT have any tutorial.

Each time before the tutorial, the TA will make an
announcement on Canvas and send an email to everyone

4
 Textbook
Econ 3334

Required:
Stock, James H., and Mark W. Watson.
Introduction to Econometrics. (3rd edition) Pearson.

This book is available at HKUST book store.

Recommended:
Jeffrey M. Wooldridge.
Introductory Econometrics. (4th edition), South-Western.
Peter Kennedy.
A Guide to Econometrics. (6th Edition), Wiley-Blackwell

5
 Web page Econ 3334

The course materials will be posted on: canvas.ust.hk.

You should be able to log into the course web site using
your regular ITSC account name .

Throughout the semester, TA and I will make

announcements through the mail function in Canvas.

Make sure to check Canvas at least twice per week for

announcements and course materials.

6
 Stata / R Econ 3334

You will need access to Stata and R, which are commonly used
statistical software.

You do NOT need to buy Stata: Lab LSKG021 has it.

I will reserve some time slots for ECON3334. The detailed
time slots will be announced on Canvas.

Other time slots depend on whether the lab is occupied.

R is free: https://www.r-project.org/

I will walk you through Stata and R during the lectures or
tutorials.

Other popular software: Matlab, Python

You can choose your favorite software.
 Problem Sets
Econ 3334

There will be 6 assignments, each of which will carry a

weight of 3% towards the final grade.

The lowest grade will be dropped.

Group study and free discussion are encouraged. But
you should submit your own answers. Copying others’
answers will be treated as cheating.

If you have any question on the problem sets, please
ask me or TA’s during our office hours. Our office
hours are for you.

Each problem set is to be handed in at the beginning of
class on the day it is due
8
Exams Econ 3334

There will be one mid-term exam and one final exam.

The mid-term carries a weight of 30%.

The final exam has a weight of 55%.

The final is cumulative and will cover all the course
materials.

9
Exams (cont’d) Econ 3334

All exams will be closed book.

There will be no make-up exams. If you miss a midterm,
you will receive a zero. The only exception is a verifiable
medical reason, in which case the weight of the missed
mid-term will be shifted to the final.

Finally, if you are caught cheating, you will receive a
zero on the exam, may fail the course, and may be
subject to further disciplinary action by HKUST.

10
 Summary of Grading Econ 3334

Assessment Activities Weighting

Problems sets 15%
Mid-term 30%
Final Exam 55%

What’s an A? A-? B+? etc…

It all depends on how everybody does at the end of the
course and where you lie in the distribution.

11
 Lecture Attendance Econ 3334

PLEASE come to class because…
 There is a lot of material, and I will go over the
most important topics during class.
 You are responsible for everything presented during
lectures.
 I may check attendance and give bonus points.

 ???

12
Class Rules
Econ 3334

No electronic devices (e.g., phone, etc.).
• http://youtube.com/watch?v=hut3VRL5XRE
• http://www.youtube.com/watch?v=spKuQAdf5r8&feature=related

Drinks and small snacks are fine, but please don’t
bring a seven-course meal.

You can sleep, but you can’t snore.

Please no excessive talking during lectures (including
talking in your sleep).

???
Office Hours Econ 3334

Xun Lu

Office Hours: 11:30am-12:30pm, Monday in
LSK6077 or by appointment, or ANY time you can
find me.

I prefer talking to you in person. I feel that Email is
not a very efficient way to ask econometric questions.
However, if you have a time conflict, feel free to drop
us a line. Please include “ECON3334” in your
subject.

If you don’t receive my reply in 2 days, send it again.

I wish I can get to know each of you. So feel free to
stop by with questions or anything you want to share.

14
Enrollment problem? Econ 3334

Please send email to Leonna
[email protected]
or

find Leonna at the general office of Department of

Economics (6th floor, LSK). (Avoid lunch time: 1-
2pm).

15
 How difficult is this course? Econ 3334

Some comments from previous students:

Too easy?
“The professor could include more mathematics in the course, like
proof…I cannot see much value in ECON3334 if it still focuses on the
non-mathematical materials.”
“can discuss some topics in depth, too easy for this course”

Too difficult?
“the course content is rather difficult for people without solid
mathematics background.”
“i think the course involves too much calculations and mathematical
proof”
“The course requires a lot maths derivation and non-maths students
need great effort to catch up.”
16
 How difficult is this course? Econ 3334

A mathematic background assessment today for two reasons:

It will provide useful information for me to design the course

It will provide useful information for you to decide whether
to enroll in this course

It has absolutely nothing to do with your course grade. But

please try your best.

17
 How useful is this course?
Econ 3334

It is very useful for your future career

These methods are widely used in business, finance and
many related fields.

Example: economics consulting firms, financial companies

Also these methods are widely used in empiric research.

18
Advice for this course Econ 3334

Read the textbook and lecture notes before coming to the
lecture. You have to read it anyway.

Practice the questions at the end of each chapter and play
with Stata

You need to follow the course step by step.

For example, you need have a good working
knowledge of probability and statistics in order to
understand regression with one regressor

You need have a good working knowledge of
regression with one regressor in order to
understand regression with multiple regressors.

Talk to me or the TA if you have any difficulty
19
Advice for this course Econ 3334

“I hear and I forget.

I see and I remember.
I do and I understand.’’

--- Confucius

20
 What is econometrics? Econ 3334

Econometrics bridges the gap between abstract economic

theory and real-world data.
• For example, micro theory suggests that there is a negative
relationship between price and quantity demanded.
• We can use econometrics on actual price & quantity data to
determine if the relationship is in fact negative.

It is both an art and a science.
• Science part is the mathematics.
• Art part is creativity and judgment in applying the math
appropriately.

Basically, the goal of econometrics is to turn data into useful
information.
21
 What is econometrics? Econ 3334

An example
3,000

2000
Annual average platinum price (USD/oz)
Total Demand of Jewellery Platinum
2,500

1500
2,000

1000
1,500

500
1,000
500

0
1970 1980 1990 2000 2010 2020
Year
Total Demand for Jewellery Annual average platinum price (USD/oz)

22
 What is econometrics? Econ 3334

You can think of econometrics as being composed of

• Mathematics
• Statistics
• Economics

There are basically two types of econometrics.
• Econometric Theory - Developing the methodologies
• Applied Econometrics - Taking the methodologies and
applying them to data.

23
 Data types
Econ 3334

Cross-sectional data: data on multiple entities (e.g.,

consumers) for a single time period.
Example: GDP of all the 50 states in the U.S. in 2012.

Time series data: data for a single entity collected at
multiple periods.
Example: GDP of California from 1990 to 2012.

Panel data: data for multiple entities in which each entity
is observed at multiple periods
Example: GDP of all the 50 states in the U.S. from 1990
to 2009

Econ 3334 focuses on Cross-sectional data!
24
 Data types
Econ 3334

Data1 : Country Year GDP Unemploy.

USA 1991 9.5 8
China 1991 7.4 11
Canada 1991 8 7

Data 2 :
Country Year GDP Unemploy.
USA 1991 9.5 8
USA 1992 9.7 7.5
USA 1993 9.8 8.1

25
 Data types
Econ 3334

Data 3 :

Country Year GDP Unemploy.

USA 1991 9.5 8
USA 1992 9.7 7.5
USA 1993 9.8 8.1
China 1991 7.4 11
China 1992 8.8 9.1
China 1993 8.9 8.4
Canada 1991 8 7
Canada 1992 9.2 7.6
Canada 1993 9.1 8.1

26
 Data types
Econ 3334
Real data example: www.gapminder.org/tools/

27
Why econometrics? Econ 3334

Two main purposes of econometrics:

• Estimating the causal effects of X on Y
• Forecasting

28
Causal effects Econ 3334

Example:

Why do you want to come to UST for a college
degree?

How do you convince me?

How do you quantify your results?

29
Causal effects Econ 3334

Example:

Economic theory (micro and macro) suggests important
relationships, often with policy implications, but virtually
never suggests quantitative magnitudes of causal effects.
• What is the quantitative effect of reducing class size on student
achievement?
• How does another year of education change earnings?
• What is the price elasticity of cigarettes?
• What is the effect on output growth of a 1 percentage point
increase in interest rates by the Fed?
• What is the effect on housing prices of environmental
improvements?

30
Causal effects and experiments Econ 3334

Ideally, we would like an experiment

In economics, we rarely have the ability to conduct
controlled experiments.

In bio, chem, & physics, they can conduct controlled
experiments in a laboratory.

If you can do an ideal experiment where the only thing
that changes is the treatment, then whatever that
treatment's effect is on an outcome is the causal effect.
· E.g., a pharmaceutical company wants to know the
effect of a new drug on weight-loss.

31
Causal effects and experiments Econ 3334

Pharma Example - Ideal Experiment

E.g., a pharmaceutical company wants to know the
effect of a new drug's effect on weightloss.
• They gather 500 lab rats.
• They split the rats randomly into two groups:
treatment and control.
• They give the treatment group the weightloss dose
for 6 months.
• They give the control group a "fake" dose
(placebo) for 6 months.

32
Causal effects and experiments Econ 3334

Pharma Example - Cont'd

After the 6 months, they weigh each rat

• Avg. weight of treatment group = 12 oz.
• Avg. weight of control group = 15 oz.

The causal effects: 12oz-15oz=-3oz.

33
 Causal effects Econ 3334

The Problem in Economic Studies

• The problem that we have in economics is we don't have
the ability to conduct ideal experiments.
• We can only do observational studies rather than ideal
experiments.
 E.g., suppose we want to obtain the causal effect of a
cigarette tax on cigarette consumption.
 We don't have the ability to split the country into two
random groups of people.
 We can't impose the tax on one group (the treatment),
while not imposing the tax on the other group
(control). 34
 Causal effects Econ 3334

The Problem in Economic Studies

• To make matters worse, a bunch of things might be
changing at the same time.

But econometrics gives us a way to control for other
stuff that might be changing, and gives us some
solutions to obtaining causal effects even without being
able to do ideal experiments.

35
Forecasting Econ 3334

A very useful aspect of econometrics is it gives us tools
to predict or forecast events that haven't occurred.

36
 Forecasting
Econ 3334

Shanghai A share index

37
Forecasting Econ 3334

Other example:
• Intel Corp. might be interested in forecasting
microprocessor sales next year.
• Labor analysts might be interested in forecasting
unemployment next year.
• Pepsi might be interested in predicting how popular a
new product line will be.

38
 Data sources
Econ 3334

If you can do an experiment, then you can just get that data
and do some simple stats for the analysis.

Otherwise, you have to rely on observational data.

US data
• Macro data is available from the Fed, BEA (Bureau of Economic
Analysis), BLS (Bureau of Labor Statistics).
• Demographics data is available from the BLS and the Census Bureau
• CPI and PPI is available from the BLS…

Hong Kong data:
• Hong Kong monetary authority…

Company stock data is available from many internet
sources (Bloomberg, Yahoo, etc.).

A lot of data is private information or difficult to obtain.
39
Main Topics Econ 3334

Review of probability theory

Review of basic statistics

Simple linear regression: Estimation and Inference

Multiple regression: Estimation and Inference

Nonlinear regression function

Internal and external validity

40
Main Topics Econ 3334

Learn methods for estimating causal effects using

observational data

Learn some tools that can be used for other purposes;
for example, forecasting using time series data;

Focus on applications – theory is used only as needed
to understand the whys of the methods;

Learn to evaluate the regression analysis of others –
this means you will be able to read/understand
empirical economics papers in other econ courses;

Get some hands-on experience with regression
analysis in your problem sets.
41