Data & Policy Summer School Program

Required Modules Sample Syllabus (2024)

Professors: Austin Wright (Program Lead and Academic Track Lead) and Jeff Levy (Professional
Track Lead)
Head TAs: Jose Macias and Alex Sobczynski
Teaching Assistants: TBD

Course Description
This course is an introduction to research design and data analytics. We will focus on establishing a foundation
for studying public policy problems through data. This course consists of two complementary sections – Data
Analytics and Programming in R. These two sections compare to one full course at the University of Chicago
Harris School of Public Policy.

Data Analytics [DA] provides an introduction to the statistical foundations, tools, and methods employed by
public policy researchers. In this section we will explore the fundamental problem of causal inference, and learn
how to use data, research design, and statistical modeling to navigate around this problem. The suite of tools
taught for DA shall depend on your track.
E

Programming in R [R] introduces students to the powerful statistical modeling software known as R. This is
a free and open source software that is constantly being expanded and upgraded. Knowledge of programming
PL

in this language is in high demand in policy job markets. In this section of the course, you will be introduced to
many of the key uses of the software — including data wrangling, applications of causal inference methods, data
visualizations, and more. The suite of tools taught for R shall depend on your track.
M

The Capstone is an opportunity to apply the coursework of Data Analytics and R Programming in a research
project with open access data. Datasets have been selected in three areas and students may choose one based on
interest. One or two of these datasets shall serve as the basis for a couple of assignments in the Programming in
SA

R assignments. You will work with a small group of peers ("capstone group") to collaborate and share ideas, but
you will each submit an individual project. Each student must submit a project that reflects independent work.
The final product is something you will be able to showcase in your resume, LinkedIn, job, or graduate school
application. Professional track students will provide a Policy Memo while academic track students will deliver
Research Notes. Capstone topics may include:

1. Economic Policy - Labor Market shifts due to automation in the early 20th century among telephone
operators also known as “Hello Girls”
 2. Urban and Social Policy - Chicago Array of Things; Analyzing the environmental, air quality, and
computer vision data collected from sensors at Chicago bus stops.
3. International Development Policy - Identifying social and economic change at the household level in
Ghana with survey data over nearly a decade from the Yale Economic Growth Center.

Virtual Format
Academic lectures for Data Analytics and R Programming are delivered via weekly video modules (pre-recorded
lectures). These modules will provide students with the knowledge and materials to understand the basics of
data analytics as applied to public policy. During the Capstone Weeks, faculty will host synchronous lectures
for each research project. You are strongly encouraged to attend the synchronous lecture. Live office hours are
held multiple times throughout each week, enabling students to connect with faculty and graduate teaching
assistants. The schedule and how to access the virtual office hours will be available on the Canvas calendar.

Course Materials
All necessary course materials will be made accessible via Canvas. There are no required textbooks. If you
would like a supplementary text that covers many of the same topics, then we recommend by category the
following:
Data Analytics:
● Thinking Clearly With Data: A Guide to Quantitative Reasoning and Analysis by Bueno De Mesquita
and Fowler.
● Mastering `Metrics: The Path from Cause to Effect by Angrist and Pischke is recommended for
Quantitative Analysis.
E

● Mostly Harmless Econometrics by Angrist and Pischke.

R Programming:
PL

● R for Data Science (R4DS) by Hadley Wickham and Garret Grolemund

○ This online textbook is free, and a new version has been posted as well.

Assignments and Grading

M

The graded assignments for this course will consist of homework assignments. Each homework assignment will
be released via Canvas, and you will submit your homework in Canvas by the required deadline. The
SA

assignments will be due on Mondays following Weeks 1, 2, 4 and 5 by 12:00 pm Central Daylight Time, and
include separate evaluations for both R Programming and Data Analytics.

The concept quizzes will be available after each video lecture, and the questions will relate directly to content
from the preceding lecture. These concept quizzes will be an excellent way to gauge your knowledge of the
material covered in lecture, and they will prepare you for questions on your homework assignments. Concept
quizzes are optional and not graded.

Communication
Communication from instructors and TAs to students will happen through posting of materials on Canvas,
including postings to Announcements and on Ed Discussion.

The most effective way for the teaching team to support students is for student to submit questions in the
following forms:

● Questions regarding course material should be asked in the live Office Hours or posted on Ed Discussion,
a forum that is monitored by the teaching assistants and instructors.
● Questions regarding scheduling should be directed to the Head TA.

Ed Discussion Board: This course will also have a dedicated Ed Discussion board. Ed Discussion is a free
online gathering place where students can engage with each other regarding course material, under the guidance
of their instructors. Setting up an ed discussion account will be part of your first assignment, but participation
is optional. On Ed Discussion, you can both ask and answer questions related to homework assignments and
course materials. If you provide a strong answer, one of the teaching assistants might endorse your answer.

R Resources
In HW1, you will download R and RStudio. Please use the following resources to do so.

Download R: here.

Download R Studio: here

E
Guide for Downloading R: here
PL
M
SA
Schedule
Week Academic Track Professional Track Assignments

Data Analytics R Programming Data Analytics R Programming

Week 1.1 - Foundations of Causal 2.1 - Intro to R and 1.1 - Foundations of Causal 2.1 - Intro to R and RStudio HW1 - 10 pts
1 Inference for Public Policy RStudio (working dirs, Inference for Public Policy (working dirs, projects, (6/17)
projects, panes, R basics, panes, R basics, etc)
etc)

1.2 - Fundamentals of 2.2 - Intro to tidyverse,

1.2 - Fundamentals of 2.2 - Intro to tidyverse, Working with Data fundamentals of data, basic
Working with Data fundamentals of data, basic visualization
visualization

Week 1.3 - Difference in means: 2.3 - Tidy data, data 1.3 - Difference in means: 2.3 - Tidy data, data HW2 - 30 pts
2 RCTs (experimental ideal) wrangling, and simple data RCTs (experimental ideal) wrangling, and simple data (6/24)

E
cleaning cleaning
PL
1.4 - Bivariate regression: 2.4 - Data visualization and
1.4 - Bivariate regression: 2.4 - Data visualization and properties, testing, exploration (ggplot2,
properties, testing, exploration (ggplot2, interpretation summarization)
interpretation summarization)
M

Week 1.5 - Multivariate 2.5 - APIs and policy 1.5 - Multivariate regression: 2.5 - APIs and policy
3
SA

regression: testing, applications (working with testing, interpretation, applications (working with
interpretation, omitted Census data) omitted variable bias Census data)
variable bias
 2.6 - Programming concepts 2.6 - Programming concepts
(for loops, functions, (for loops, functions,
control flow) control flow)

Week 1.6 - Functional Forms, 2.7 - Descriptive stats in R Catch up Week and Review 2.7 - Descriptive Statistics, HW3 - 30 pts
4 Interactions, and Indicator (sample, distribution) Existing Materials Visuals, and mapping (7/8)
Variables introduction in R
(distributions, ggplot2)

1.7 - Binary Dependent 2.8 - Presenting a model;

Variables Causal inference in R (lm,
stargazer)
1.8 - Differences in
Differences

1.9 - Panel data designs: 2.9 - Literate programming - 2.8 - More Advanced Data HW4 - 30 pts
fixed effects, first (RMarkdown, code syntax) Visualization and Mapping (7/15)
Week
differences 2.9 - QGIS Introduction
5

E
2.10 - Presenting Models
(Required for Professional
Track, Optional for
PL
1.10 - Regression Graphically (RD, DiD) Academic Track)
discontinuity designs

1.11- Instrumental
M

variables

Week
Capstone Project (Friday, 7/26)
6
SA

Week
7
Credential Award
In order to pass this course, you must successfully pass at least two of the three academic components: Data
Analytics, R Programming, and Capstone research project. The passing score in each of the three components is
60%.

Upon successful completion of the coursework, you will be issued a Certification of Credential Completion by
the University of Chicago Harris School of Public Policy. The Certification of Credential Completion contains
a point grade for each academic component: Data Analytics, R Programming, and Capstone research project.
You will receive an email from our office ([email protected]) with the electronic certification
approximately four weeks after the program.

You will additionally receive an official UChicago Transcript with pass/fail marks (non-credit) for each
academic component: Data Analytics, R Programming, and Capstone Research project. You will be able to
access this transcript at the end of the summer (approximately early October). This is a non-credit program.

Sample Certification of Credential Completion

For your reference, we have enclosed a sample of a past Certification of Credential Completion, which contains
a point grade for each academic component: Data Analytics, R Programming, and Capstone research project.
E
PL
M
SA
SA
M
PL
E