Syllabus for QSS UTokyo (Summer 2022)
Kosuke Imai (Head Instructor)
imai [at] Harvard [dot] Edu
https://imai.fas.harvard.edu
Claire Liow (Teaching Assistant)
yijialiow [at]
g.ecc.u-tokyo.ac.jp
Anna Yorozuya (Teaching Assistant)
yorozuya-anna [at]
g.ecc.u-tokyo.ac.jp
Xiaolong Yang (Course Assistant)
yang-xiaolong0406
[at] g.ecc.u-tokyo.ac.jp
Sho Miyazaki (Course Assistant)
sho.miyazaki.2000 [at]
keio.jp
Would universal health insurance improve the health of the poor? Do patterns of arrests in US cities show evidence of racial profiling? What accounts for who votes and their choice of candidates? This course will teach students how to address these and other social science questions by analyzing quantitative data. The course introduces basic principles of statistical inference and programming skills for data analysis. The goal is to provide students with the foundation necessary to analyze data in their own research and to become critical consumers of statistical claims made in the news media, in policy reports, and in academic research.
Tuesdays and Thursdays 10:25AM–12:10PM. The class will be taught
virtually until June 9 and will meet in person from June 14.
We will begin each class with a lecture, which will be recorded and
posted at Perusall. After the lecture, students will work in pairs on
exercises. The class ends around 12:00PM and the instructor and TA/CAs
will be available until 12:10PM to answer any remaining questions.
– Instructor: By appointment. Email to set up a virtual (before June 9) or in-person (after June 14) meeting. In-person office hours will be held on Tuesdays and Thursday early afternoon (1:30PM and 2:30PM).
– Each teaching/course assistant will have different office hours and we encourage you to sign up from the appointment links in the contact information section. You are welcome to ask any questions. Besides these individual-based office hours, there will be a groupbased office hour every Friday 9AM-10AM to discuss the in-class exercises and other questions raised.
Please first set up your own account at https://www.perusall.com/, and then enroll with the
course code that we provide you with. Please be sure to set up your
Perusall account with your UTokyo email so we are able to identify you,
and do not share the course code with others. We will provide two
manuscripts (baseR and tidyverse) of the QSS
textbook on Perusall. There is no need to purchase the book though the
published version will contain fewer typos and mistakes than the
manuscripts. Perusall allows you to annotate, comment and ask questions
directly on the textbooks and the lecture recordings. Perusall is also a
great way to ask questions about the course materials and the problem
sets. A major advantage of this platform is that other students can
benefit from the questions and answers. Please feel free to respond to
questions that you can answer!
The course requirements consist of the following four components:
qsslearnr-tidy
before each class. These exercises will be graded only for
completion.baseR and tidyverse version of the
tutorials are available, it is mandatory to complete
the baseR version. The tidyverse version is
not only strongly recommended, but also gives you bonus
points that will eventually add up to your overall grades.To begin pre-class exercise, first install several packages by typing the following commands at the R console (please make sure every package is installed in the following order):
install.packages("remotes")
remotes::install_github("kosukeimai/qss-package", build_vignettes = TRUE)
remotes::install_github("rstudio/learnr")
remotes::install_github("rstudio-education/gradethis")
remotes::install_github("annayrzy/qsslearnr-tidy")
This needs to be done only once. Then, you will be able to see all available tutorials via the following command,
learnr::run_tutorial(package = "qsslearnr")
Then, start a tutorial of your choice by, for example,
learnr::run_tutorial("00-intro", package = "qsslearnr")
learnr::run_tutorial("tidy-01-causality1", package = "qsslearnr")
When you are done, you should download a submission report and then
upload it to GradeScope. Please be aware that all the
files with the title ”XX-chapter” are in baseR, while those
that that are titled ”tidy-XX-chapter” are written in
tidyverse.
In-class Exercises (20%): You will be paired up each week with another student in class to work on exercises. You will begin to work on exercises during each class meeting. You will then be asked to submit a single, joint solution (as a single PDF file) for selected questions to GradeScope before the next class.
Take-home midterm and final exams (60%): There will be two open-book take-home exams. Students will have 24 hours to work on each exam, and students can decide when to start the exam during the exam periods (midterm: JUNE 15 - 22; final: JULY 11 - 18). No collaboration is allowed, and students SHOULD NOT discuss their contents with anyone before submission. Each take-home exam is equally weighted.
For all assignments, late submission is not allowed without at least 24 hours prior notice.
Imai, Kosuke (2017). Quantitative Social Science:
Introduction. Princeton University Press.
Translated versions: Japanese; Chinese; Korean.
More accessible version: Data
Analysis for Social Science: A Friendly and Practical
Introduction (forthcoming in 2023)
This course proceeds at a fast pace. It is important for you to keep up with the course materials each week.
Reading assignments: You are expected to read the assigned sections of the textbook before each class. We strongly encourage you to try out the commands in the book. For your convenience, all the data sets and commands used in the book are available as vignettes of the qss package (the installation instruction is given above).
Pre-class exercises: These exercises are useful for making sure
that you have understood the basics of R covered in each
section of the textbook. Try these out after completing the reading
assignment. Submit your tutorial completion report by 10AM on the day of
each class.
In-class exercises: During each class, you will be working with your assigned partner on the exercise. Submit your joint solution to the selection questions by 10AM on the day of the next class. For example, the Monday in-class exercise will be due 10AM on Friday.
| Class/Date | Topic | Textbook |
|---|---|---|
| Class 1 (May 24) | Introduction (overview; intro to R) | Chapter 1 (Section 1.3) |
| Class 2 (May 26); Class 3 (May 31) | Causality (randomized experiments; observational studies) | Chapter 2 (Section 2.1-2.4; 2.5-2.7) |
| Class 4 (June 2); Class 5 (June 7) | Measurement (survey sampling; clustering) | Chapter 7 (Chapter 3 (Sections 3.1-3.4; 3.5-3.7) |
| Class 6 (June 9); Class 7 (June 14) | Prediction (Prediction and Loop; Regression) | Chapter 4 (Section 4.1; 4.2-4.3) |
| Midterm Exam June 15 - 22; No class 8 due to the midterm | - | - |
| Class 9 (June 21); Class 10 (June 26) | Probability (Probability and conditional probability; Random variables and their distributions, Large sample theorems) | Chapter 6 (Sections 6.1-6.2; 6.3-6.4) |
| Class 11 (June 28); Class 12 (June 30); Class 13 (July 5) | Uncertainty (estimation; hypothesis tests; regression with uncertainty) | Chapter 7 (Section 7.1; 7.2; 7.3) |
| Final Exam July 11 - 18 | - | - |
Text and figures are licensed under Creative Commons Attribution CC BY-NC 4.0. The figures that have been reused from other sources don't fall under this license and can be recognized by a note in their caption: "Figure from ...".