• This module covers a paper that uses instrumental variables analysis to find causal effects of strong property rights on a country's economic development.

  • Josh Angrist’s study of the impact of military service on lifetime outcomes is an influential paper in the social sciences. These videos explain why he chose to examine this topic, the methods he used, and the outcomes he found.

  • This module covers the basics of Instrumental Variables Analysis, including the concepts, uses, and pros and cons of IV analysis.

  • First applied to the evaluation of scholarship programs, this quasi-experimental pretest-posttest design has become increasingly popular in recent years.

  • This module outlines some of the vocabulary used to discuss cause and effect in science.

  • The Local Average Treatment Effect (LATE) can be helpful when noncompliance is an issue. This module will walk you through how to compute the LATE and how to interpret it.

  • We wrap up the Causal Inference Bootcamp by looking at how the different techniques we've talked about can work together, and what choices you might have to make as you start your analysis of data.

  • We've covered a lot of ways to look at your data to find causal connections, but in the real world, you usually don't get a perfect dataset or a simple situation where assumptions can be foolproof. How do we balance the strength of our data with the strength of our assumptions?

  • This module introduces how we see regression in research for Economics 339: Environmental Economics & Policy.

  • This module covers different examples of social science experiments to show you how they're set up and what they can reveal.

  • This module takes you through several examples of instrumental variables analysis, showing you how researchers deal with its strict requirements in different datasets.

  • We work through some examples of how modeling can be insightful in this module.

  • This module shows examples of panel data analysis using difference-in-differences from research papers.

  • This module covers examples of regression in social science research, from seeing how people have studied the effect of giving property to the homeless in Argentina, to seeing how serving in the military can affect your ability to earn more money in post-military jobs.

  • Get started with the basics of social science experiments in this module.

  • This module covers the basic ideas and issues in determining causation.

  • Researchers studying Switzerland look to a religious war between Catholics and Protestants in 1520 to analyze modern social divisions.

  • This module takes you through the concepts and implementation of the Local Average Treatment Effect (LATE) that's increasingly popular with social science researchers.

  • Learn a few of the starting points behind the how and why we use models instead of experiments.

  • This module goes through a few examples of how natural experiments have been used to discover causal effects.

  • When experiment subjects don't do as requested, it can cause problems with your experiment and your data collection. This module covers some of the basic ways to deal with noncompliance.

  • When survey subjects don't respond as instructed, it can create issues for your survey data. This module covers what options researchers have for proceeding when subjects don't answer questions.

  • This module describes the basics of setting up and analyzing a randomized experiment, and why they can be hard to find in social science.

  • Just need the basics for understanding what a regression is, and what the pros and cons are to using them to find causal effects? This module will get you started.

  • This module uses regression discontinuity to analyze how a school's quality affects the price of houses in its assignment area.

  • The deadly London Cholera Outbreak of 1886 is a fascinating and pivotal moment in the history of public policy, epidemiology, and social science. Learn about what happened, and how one early scientific trailblazer turned it into a critical teaching moment.

  • The Oregon Healthcare Experiment was one of the most comprehensive studies ever done on the effect of healthcare coverage. In this module, we cover it from initial assumptions and setup to its results.

  • This module takes a look at the seminal paper to show how its problem solving techniques set the groundwork for today's regression discontinuity techniques.

  • This landmark study examined the long-term effects of providing preschool to underprivileged children. This module describes how the scientists were able to find causal effects in the study.

  • When the Argentinian government gave property rights to squatters living on largely unclaimed land, the opportunities for natural experiments arose to see what health, economic, and other effects might come from this policy change. This module walks through a couple of examples.

  • Experiments don't always go smoothly. This module covers some of the main challenges you might face when planning and conducting an experiment.

  • Instrumental Variables Analysis is a tricky and subtle tool, with high requirements and a lot of potential pitfalls. This module covers the main issues you'll run into when reading or doing an IV analysis.

  • What are the biggest pitfalls to avoid when trying to figure out cause and effect? There are some common issues that can add confusion to any conclusions, particularly in social science research.

  • Tables in research papers can present a vast amount of information. How do you know where to look for key results? How can you find out what assumptions lie beneath the numbers? Do they have anything in common with one another? This module looks at examples for guidance.

  • If you run an experiment, what are the best ways to deal with the data you get out of it? What are the pitfalls you should avoid? This module will get you started.

  • This module includes all of the experiments from the Causal Inference Bootcamp and discusses how treatments and controls can exhibit causal effects.

  • This module of the Causal Inference Bootcamp explains the basic concepts of IV analysis and how social scientists use it to indirectly find causality in their data.

  • We cover the main ways that researchers take limited data and make choices about their assumptions and expectations in order to create models of behavior for when experiments are extremely difficult or even impossible.

  • This module walks you through the basic concepts of panel data, referencing a few examples and discussing the benefits and potential trouble spots.

  • This module includes videos on what a regression is, what it will look like in a paper, and the benefits and pitfalls of using and interpreting regressions for causal inference.

  • In its simplest form, regression discontinuity is a pretest-posttest program-comparison group strategy. It can be a useful method for determining whether a program or treatment is effective.