[http://cameron.econ.ucdavis.edu/e190/e190syl.html]

Department of Economics, University of California - Davis

FALL 2023

Professor Colin Cameron, 1124 Social Sciences and Humanities

Email: accameron@ucdavis.edu Website: https://cameron.econ.ucdavis.edu/

**Meeting: **Tuesday and Thursday 1.40-3.00
pm Bainer 1060 **(In person)**

**Office Hours: **Tuesday
3.30 - 5.00 pm

Wednesday 3.30 - 5.00 pm

**Teaching Assistant:**

Kathya Tapia kattapia@ucdavis.edu

Office hours: Tuesday 11.00am - 1.00 pm SSH 0118

**Discussion Sections:
**

The course goals are to introduce students to research applying basic regression methods to data.

(1) Students write a research paper based on analysis of economics data.

(2) Cover some basic regression methods, especially for causal analysis.

(3) Assignments will including downloading and cleaning data (from IPUMs), some basic regression analysis, and replication of a published journal paper.

(4) Teaching will use Stata. Projects can use Stata, R or Python.

The course is intended for Economics majors, and first Pass is restricted to Economics majors.

Enrollment is capped at 30 students.

Should there still be room after first pass I will consider students who have taken STA 108 with a grade of B- or better or ARE 106 with a grade of B- or better, provided they have also taken basic economics courses in ECN or ARE.

**COURSE OUTLINE: **

Classes will be a mix of teaching necessary methods and student presentations.

COURSE MATERIALS

For your project you can use Stata, R or Python.

Key material will be posted at the course Canvas site (http://canvas.ucdavis.edu) under Files

- Below I give references to

This is a relatively inexpensive book (available as pdf or print) that provides an introduction.

- Undergraduate level treatments that are a bit more more advanced are available in the standard texts

Jeffrey Wooldridge

To get started in Stata see http://cameron.econ.ucdavis.edu/stata/stata.html and especially http://cameron.econ.ucdavis.edu/stata/stataintro.html

Stata is installed in computer labs

It is also available after hours in the

You
can also purchase your own copy of Stata (recommended) - go to
https://www.stata.com/order/new/edu/gradplans/student-pricing/

For this course and other economics classes the cheapest
version Stata/BE is more than adequate and costs $48 (6
months), $94 (1 year); $225 (permanent copy).

To install Stata after it is purchased:

(1) Choose the correct operating system (e.g. Windows or Mac);

(2) Choose the correct version of Stata - the student price
version is Stata/IC;

(3) When you first run Stata after installation it will ask
for an "authorization code". These codes are given in a pdf
attachment you will received in the email from Stata following
purchase (some codes are lengthy and it is easiest to cut and
paste them in).

The
Stata code used in my ECN 102 text is at https://cameron.econ.ucdavis.edu/aed/aedSTATAprograms.html

And the datasets are at https://cameron.econ.ucdavis.edu/aed/aeddatasources.html

For
more advanced Stata my book https://cameron.econ.ucdavis.edu/mus2/
can be accessed online through the UCD library. All the data and
code for that book are available free at https://www.stata-press.com/data/mus2.html

**R**** for
regression:****
**R can be downloaded to your own computer free.

I have some older notes at https://cameron.econ.ucdavis.edu/R/R.html

**Project:
**The key component of this class is a
research paper which will be a group project (2 students per
paper depending on class size).

**COURSE OUTLINE**

Class 1: Regression basics and Stata

Files tr_basics.pdf, basics.do and AED_EARNINGS_COMPLETE.DTA **at
Canvas**

Classes 2 to 8: Introduction to Causal Methods** **In order
go through the following topics with slides posted at https://cameron.econ.ucdavis.edu/causal/

- Randomized control trials (RCTs) AED 14.2 and 13.5

- Instrumental variables (IV) AED 17.4, Appx C.3 and data example 13.8

- Directed acyclic graphs (DAGS)

- Panel data and fixed effects (FE) AED 17.1, 17.2 and 17.3

- Differences-in-differences (DID) AED 17.5.4 and data example 13.6

- Regression discontinuity design (RD) AED 17.5.7 and data example13.7

- Synthetic control

- Treatment evaluation (TE) AED 17.5

Also Brief Introduction to Machine
Learning

** **

Classes 9
to 10: Project
development and discussion

Classes
11: Midterm exam

Classes 12 to 13: Projects
discussion and additional methods

Classes 14 to 15: Project interim presentations

Classes 16 to 18: Projects discussion and additional methods

Classes
19 and 20: Final project presentations

**COURSE GRADING **

**Attendance:
5% **Attendance is
checked at each class. Lose 1% for each
class missed beyond two missed classes in the quarter.** **

**Assignments: 30% **Due 10 a.m.
on (1) Friday October 6, (2) Wednesday October 18, (3)
To be determined.** **

**Midterm Exam:** ** **15

Project interim Presentation: 5

**Assignments** are posted on Canvas under **Files
/ Homeworks**.

They are to be turned in as a **single pdf file** on Canvas
under **Assignments** by 10 am on Fridays.

For how to include Stata results see USING STATA AND SAVING
RESULTS.pdf posted on Canvas
under **Files / Homeworks.**

**Course grade** is determined by the total
score, with weights given above.

(1) All undergraduate and graduate course outlines (syllabi) should list or provide a link to the U.C. Davis Code of Academic Conduct which is at https://ossja.ucdavis.edu/code-academic-conduct. This provides many leading examples of academic misconduct. You should read this.

(2) One specific example of academic honesty is copying from solutions to assignments given in previous 132 courses.

(3) If an instructor has a reasonable suspicion of academic misconduct, whether admitted by the student or not, the instructor shall report the matter to the Office of Student Support and Judicial Affairs.

(4) The instructor has authority to determine a grade penalty when academic misconduct is admitted or is determined by adjudication to have occurred; with a

maximum grade penalty of “F” for the course.

Note that Student Support and Judicial Affairs may separately impose sanctions for academic misconduct, including community service, suspension and dismissal.