Syllabus
Instructor
Course Details
- Mon/Wed
- January 14th - April 29th
- 5:15-6:44 PM
- PCPE 202
- Slack
Course Description and Objectives
Global development increasingly relies on data and quantitative evidence to inform policies. Thus, the growth of new data sources and advances in computational tools have expanded what researchers can study and how well they can study it, creating the possibility of better-informed responses to long-standing challenges such as poverty, inequality, and governance.
However, more data alone does not guarantee better policy. This course examines how contemporary social science research uses data to make claims about development and governance, and how to evaluate those claims critically. Students will engage with recent research and gain hands-on experience analyzing real-world data using common research designs and computational tools, with an emphasis on transparency, inference, and reproducibility.
The course will be organized around several timely substantive topics in global development. As we explore these topics, students will gain a deeper understanding of the challenges that shape governance and development. At the same time, students will be introduced to data analysis methods, inferential techniques, and computational tools that are useful across a wide range of applications. Specifically, students will deepen their understanding of basic statistical methods common to the social sciences, learn how these methods can be used to make inferences about population characteristics and causal relationships, and prepare documents that contain reproducible data analysis workflows.
At the end of the course you should be able to:
- Evaluate the quality of evidence in the development field
- Think clearly about how data can be used to learn about development and governance challenges
- Use tools for data analysis such as R, RStudio, Quarto, and GitHub
- Produce professional-quality documents that summarize original research
This class is designed as a follow-up to PSCI 1102. Students that have not taken PSCI 1102 and PSCI 1800 (or an equivalent) should contact the instructor before enrolling.
Course Materials
This course relies primarily on free, open-source materials. However, the purchase of one textbook will be required. All other reading materials will be uploaded to this website or circulated on Slack at least one week before the meeting. Course site and instructional materials draw on content originally developed for PSCI 3200 by Jeremy Springman
Books
Students are required to purchase a copy of Data Analysis for Social Science: A Friendly and Practical Introduction (DSS). We will use DSS as a jumping-off point for this course. While students are expected to already be familiar with many of the tools and concepts covered by this book, it will serve as a method to review core concepts and orient discussion about how to expand on these skills.
I am asking students to purchase a copy of DSS because it comes with access to additional, helpful resources. If you are unable to purchase this book, you must let me know. To save money, consider e-renting the textbook.
Computing
In the course, we will be using R for data cleaning, analysis, and visualization. R is free, open source statistical computing environment available on all major operating systems. We will also be using RStudio, a free, widely used graphical interface for R. For document preparation, we will be using Quarto, a free, open-source scientific and technical publishing system that is compatible with both R/RStudio and Python, as well as several other languages. Both Quarto and RStudio are supported by a company called Posit. For version control, we will be using Github.
Students are expected to already have R and RStudio installed on the personal computer that they will be using for class. We will cover the installation of all other required computing tools during the course.
Several course requirements will require you to write and submit R code. Your code must be appropriately commented and reproducible. To ensure your code meets the course standards, please follow this style guide from Hadley Wickham (Chief Scientist at Posit and developer of ggplot2 and tidyverse).
Course Structure
Substantively, the course is divided into several parts. Part 1 presents a general introduction to the course and a brief introduction to correlation, causality and statistical inference. The remaining parts are structured around key substantive topics in development. For each topic, we will begin with a brief overview of the literature. Then, we will focus on one particular research question and use it as a guide to learn how to implement some of the most common research designs in the social sciences. Throughout, you will gain hands-on experience with diverse kinds of data through in-class workshops and data assignments. Weekly reading assignments will be divided between contemporary research on substantive topics in global development and textbook chapters focused on social science research methods. You are expected to attend class and be prepared to engage in discussion about the assigned readings.
Grading
Performance in this class will be evaluated by according to performance on the following course requirements:
| Requirement | Percent of Final Grade |
|---|---|
| Quizzes (4) | 10% |
| Workshops (4) | 15% |
| Data Assignments (3) | 35% |
| Final Project (1) | 40% |
Requirement Descriptions
There are four graded requirements for this course.
Quizzes
- You are expected to attend each course meeting. On four randomly selected meetings, there will be a brief quiz designed to test whether or not students did the readings. Students with a pre-approved absence will be required to take the quiz remotely within 24 hours of its administration (in the event your absence falls on a quiz date). Students will be permitted one pre-approved absence for the semester.
- Grade: 10%
Workshops
- We will have four workshops throughout the semester. These will be interactive, hands-on workshops allowing students to gain familiarity with new statistical methods or computational tools. These workshops will cover important tools, such as quarto and github, and data analysis tasks, including cleaning, visualization, and modeling. After each workshop, you will be required to submit a product (ex. the link to a git repo, a quarto doc, an R script, etc.) demonstrating completion of the workshop.
- Grade: 15%
Data Assignments
- There will be three data assignments throughout the semester. These assignments are designed to give you an opportunity to apply tools and methods discussed in readings, lectures, and workshops to data from the real world. These are individual assignments. While I encourage you to collaborate with your colleagues as you think through the tasks, you will be required to submit your own code and write-up.
- Grade: 35%
| Data Assignment | Due Date |
|---|---|
| Assignment 1 | Mar 4th 11:59pm ET |
| Assignment 2 | Mar 18th 11:59pm ET |
| Assignment 3 | Apr 15th 11:59pm ET |
Final Project
- The final project is a data analysis project that will use data of your choosing. The only stipulation is that this data must be relevant to one of the global development topics covered in this course. The assignment will require you to formulate a research question, find data that can help you answer that question, apply the tools and methods from this course to the data you have selected to answer your research question, and present those results for public consumption.
- The goal will be to produce a professional project that can showcase the skills that you have gained to potential employers. Your final submission will be a publicly available webpage that contains: (1) a brief introduction to your research question and data; (2) a discussion of your research design, its assumptions, and threats to inference; (3) a visualization that describes your data; (4) a presentation of the results from a regression model (as a table or graph) and discussion of its implications for your research question; and (5) a discussion of the implications of your findings for development policy or practice, including the limitations of your analysis and suggestions for future research. In addition to the public-facing webpage, you must share access to a GitHub repo that contains the code to reproduce the project output.
- Grade: 40%
- Due: May 10th 11:59pm ET
Course Policies
Please review these course policies carefully. Any questions or concerns about these policies should be raised during the first week of class.
Late Submissions and Regrading
Late submission of assignments will incur a penalty of 2 points for every day late, except in documented cases of serious illness or family emergency. If you feel there has been an error in the grading of one your assignment, you may request in writing a regrade of the assignment. First, I will request a detailed write-up of your dispute. Second, I will regrade the entire assignment, not just the part you are disputing. Therefore, your regrade might increase or decrease the overall grade on the assignment.
Use of AI Tools
You are welcome to use generative AI tools, such as ChatGPT, to assist you with your work in this course. There is mounting evidence from rigorous research that these tools increase human productivity. I believe that their use will continue to proliferate, so it is important to gain experience integrating them into professional tasks. However, AI tools frequently make errors and ‘hallucinate’ information about things that do not exist (journal articles, R functions, etc.). It is your responsibility to verify the information provided by such tools. Most importantly, you are required to disclose your use of AI tools for assignments in the form of footnotes or citations. The use of AI tools will not be counted against you. On the contrary, I want to adopt and share your clever or innovative applications of AI tools.
Electronic Devices
Laptops will be required in class. All other electronic devices should be silenced and hidden. If there is an emergency situation and your phone must be visible, please inform me at the beginning of class.
Controversial Topics and Statements
This course may deal with subject-matter that is difficult or controversial. It is crucial to approach these topics with sensitivity and openness. Students are required to treat one another with respect, even in cases of disagreement. At times, research findings may be in-tension with your normative commitments. I urge students to engage earnestly and critically with any evidence that challenges your prior beliefs.
Academic Honesty
Students are expected to follow the University of Pennsylvania’s Code of Academic Integrity. Suspected violations will be referred to university administration for disciplinary action. If you have any doubts or questions about what constitutes academic misconduct, please do not hesitate to contact me.
Mental Health
Your mental health is important to me. Struggles with mental health, as well as serious mental illnesses, are common across students, faculty, and staff. Please feel free to reach out to me about issues you are having within or outside of this course. I emphatically encourage anyone who thinks they may benefit to utilize the university resources listed below:
Please note that this list is not comprehensive. If there are services that you think should be added to this list, please let me know.
Accessibility
Accessibility is a shared value and a shared responsibility at Penn. The Weingarten Center partners with other departments throughout campus to coordinate and improve the accessibility of buildings and grounds, transportation, communication, and digital infrastructure. Students that require academic accommodations should contact the Weingarten Center. Academic accommodations are determined on an individualized basis through an interactive process that involves student self-disclosure, documentation of disability, and an initial meeting with a Disability Specialist. Accommodations do not alter fundamental requirements of the course and are not retroactive. Students should request accommodations as early as possible, since they may take time to implement. Students can notify the Weingarten Center at any time during the semester if adjustments to their communicated accommodation plan are needed.