1 - 3 of 3 results for: POLISCI 150C: Causal Inference for Social Science

Are you interested in environmental and energy policy? Do you want to improve your data science skills? If so, Empirical Environmental Economics is for you. In the first few weeks of class, you'll use data and microeconomic modeling to quantify the harms from pollution, including estimating the social cost of carbon emissions. For the rest of the quarter, you'll use more data and microeconomic modeling to evaluate major environmental policies such as pollution taxes, cap-and-trade programs, and subsidies for clean technologies. You will consider overall benefits and costs as well as the distributional equity, which can inform discussions of environmental justice. You will learn and practice useful data science skills, including applied econometrics/causal inference methods (e.g., difference-in-differences, instrumental variables, and regression discontinuity) and equilibrium modeling. The class has weekly problem sets involving data analysis in R, plus a final paper. Class sessions feature active learning, discussions, and small-group case studies. You should only enroll if you expect to attend regularly and complete the problem sets on time. Prerequisites: You must have experience with regression analysis (e.g., ECON 102 or 108, CS 129, EARTHSYS 140, HUMBIO 88, POLISCI 150C, or STATS 60 or 101).¿If you plan to take microeconomics (e.g., ECON 1, 50, or 51), we recommend you take those either beforehand or concurrently. If you have no economics background, you may still be comfortable in class if you are strong in math, statistics, and/or computer science. If you?ve not used R before, that?s OK: we will guide you from the beginning. If you have used R before, you can still learn a lot in this class through the applications.

Causal inference methods have revolutionized the way we use data, statistics, and research design to move from correlation to causation and rigorously learn about the impact of some potential cause (e.g., a new policy or intervention) on some outcome (e.g., election results, levels of violence, poverty). This course provides an introduction that teaches students the toolkit of modern causal inference methods as they are now widely used across academic fields, government, industry, and non-profits. Topics include experiments, matching, regression, sensitivity analysis, difference-in-differences, panel methods, instrumental variable estimation, and regression discontinuity designs. We will illustrate and apply the methods with examples drawn from various fields including policy evaluation, political science, public health, economics, business, and sociology. Prerequisite: POLISCI 150A.