DS-UA 201 Causal Inference
Teaching Assistant, New York University, Center for Data Science, 2023
DS-UA 201 with Dr. Parijat Dube:
Lecture: Monday 17:00 - 19:55 at 19UP 102
Lab:
Course Description
Causal Inference provides students with the tools for understanding causation, i.e., the relationship between cause and effect. We will start with the situation in which you are able to design and implement the data gathering process, called the experiment. We will then define causation, identify preconditions required for A to cause B, show how to design perfect experiments, and discuss how to understand threats to the validity of less-than-perfect experiments. In this course, we will cover experimental design and then turn to those careful approaches, where we will consider such approaches as quasi-experiments, regression discontinuities, differences in differences, and contemporary advanced approaches.
Course Overview
We often want to know the relationship between cause and effect. Almost every domain has significant causal research questions that can drive decision making. Labor economists want to know whether job training programs successfully increase participants’ wages. Epidemiologists want to know whether a particular medical treatment improves quality of life. Advertisers want to know whether a marketing campaign is effective at boosting sales. You’ve probably heard that “correlation does not imply causation.” But that raises the question: What exactly is causation and how can it be determined whether an observed relationship is truly causal?
This course will teach you the fundamentals of how to reason about causality and make causal determinations using empirical data. It will begin by introducing the counterfactual framework of causal inference and then discuss a variety of approaches, starting with the most basic experimental designs to more complex observational methods, for making inferences about causal relationships from the data. For each approach, we will discuss the necessary assumptions that a researcher needs to make about the process that generated the data, how to assess whether these assumptions are reasonable, and finally how to interpret the quantity being estimated.
This course will involve combination of lectures, sections and problem sets. Lectures will focus on introducing the core theoretical concepts being taught in this course. Sections will emphasize application and discuss how to implement various causal inference techniques with real data sets. Problem sets will contain a mixture of both theoretical and applied questions and serve as a way of reinforcing key concepts and allowing students to assess their progress and understanding throughout the course.
As a part of this course, you will be introduced to statistical programming using the R programming language. This is a free and open source language for statistical computing that is used extensively for data analysis in both academia and industry. No prior experience in programming is necessary and we recognize that students will come in with a variety of backgrounds and different levels of experience in programming. This course is designed to emphasize learning by doing and will teach statistical programming with the aim of preparing students to analyze actual data.