Courses Designed and Taught
Applied Data Science
This is an applied course that will introduce students to the python programming environment. It is intended for students who want to apply statistical analysis, information visualization, machine learning, text analysis, and data collection techniques through popular python toolkits such as scipy, numpy, pandas, matplotlib, seaborn, beautiful soup, scikit-learn, nltk, and more to gain insight into any data.
By the end of this course, students will be able to: (1) take any tabular data, clean it, manipulate it, and run inferential statistical analyses, (2) identify best practices in data visualizations, (3) identify the difference between supervised (classification) and unsupervised (clustering) techniques, and identify which technique they need to apply for a particular dataset and need, as well as, engineer features to meet that need, (4) be able to perform basic text mining and text manipulation, and (5) be able collect large amounts of data via some form of automation.
This course requires basic competency in statistics, and preferably some very basic programming knowledge (in any language). The basic programming knowledge expected involves knowing how to print statements, assign values to variables, write an if-statement, and write for and while loops. Students with no prior programming experience will be provided with a short (ungraded) assignment at the beginning of the course covering all the basic knowledge they expect to have in order to continue with the course. Students are also not expected to have any prior knowledge in machine learning algorithms either.
Computational Social Science
This course provides students with an interdisciplinary, data-driven approach to studying different social phenomena empirically. It also provides an in-depth survey of the latest research methodology and topics that prepare the students to produce high quality research in Data Science and Computational Social Science. This seminar-based course covers applications from diverse fields, such as sociology, psychology, data science, and artificial intelligence. It covers the use of computational techniques to model and predict social phenomena using real data. Students are required to complete a course project, and to write up the results in a short article.
Upon successful completion of the course, students should be able to: (1) Develop measurement strategies and research designs that can address interesting social science questions. (2) Evaluate modern cross-disciplinary research from the perspectives of both social science and computer science. (3) Identify challenges and opportunities, as well as conduct in-depth discussions in the latest literature on different topics in computational social science (4) Develop modern research proposals that blend ideas from social science and computer science. (5) Explain cross-disciplinary social science literature and methods. (6) Gain practical Python skills and apply them to data analysis.
Introduction to Programming
(designed for Masters of Science in Economics Program)
We find that the exposure of many economists to programming languages tends to be limited to mastering statistical packages, such as Stata and EViews, just well enough in order to perform simple tasks like running a basic regression. These skills, however, do not scale up in a straightforward manner to handle complex projects.
This course is designed to help address this challenge. It is aimed at Masters students who expect to do research in a field that requires modest to heavy use of computations. In other words, any field that either involves real-world data; or that does not generally lead to models with simple closed-form solutions. Students will be introduced to effective programming practices that will substantially reduce their time spent programming, make their code more dependable, and their results reproducible without extra effort.
The course draws extensively on some simple techniques that are the backbone of modern software development, which most economists are simply not aware of. It shows the usefulness of these techniques for a wide variety of economic and econometric applications by means of hands-on examples.
Winter Institute of Computational Social Science at NYU Abu Dhabi (WICSS-Abu Dhabi)
The instructional two-week program will involve lectures, group problem sets, and participant-led research projects. There will also be invited speakers who will share their experience in computational social science research. Topics covered include text as data, website scraping, digital field experiments, machine learning, ethics, and more. There will be ample opportunities for students to discuss their ideas and research with the organizers, other participants, and visiting speakers. Because we are committed to open and reproducible research, all materials created by faculty and students for the Winter Institute will be released open source.
Participation is restricted to PhD students, postdocs, early career researchers in either public or private research institutes, and early career faculty within 5 years of their PhD. We welcome applicants from all backgrounds and fields of study, especially applicants from groups currently under-represented in computational social science. About 10 participants will be invited, and participants are expected to fully attend and participate in the entire program. Those selected based on the strength of their application materials will receive financial support to cover their travel and accommodation.