Teaching resources on randomized evaluations
Since 2005, J-PAL has offered its Evaluating Social Programs course in a number of different locations worldwide. This week-long course provides a thorough understanding of randomized evaluations and pragmatic step-by-step training for conducting one’s own evaluation. In addition to offering the course in person, J-PAL also offers a free, online version in several languages. Teaching materials from the course are available in this resource page.
This lecture provides an introduction to impact evaluation, from the types of questions we can answer to how we can ensure that impact evaluations build on good program design and implementation.
- Why Evaluate slides (2023)
Theory of Change and Measurement
This lecture explores how impact evaluations build on our theories of change, how we define and measure key outcomes, types of data and where we can find them, and potential sources of measurement error.
Why and When to Randomize
In this lecture, we present different impact evaluation methodologies, including randomized evaluations, and discuss which factors can influence the choice of one impact evaluation method over another.
How to Randomize
This lecture introduces random sampling and random assignment and illustrates how the research questions of interest and real-world constraints guide randomization design choices.
Sample Size and Power
This lecture introduces the concept of statistical power and walks through the factors that influence the power of a study, including the design choices introduced in How to Randomize and the outcomes determined in Theory of Change Measurement. The lecture slides below reflect two technical tracks. The Essentials of Sample Size and Power slides cover the intuition and basic principles behind power calculations while the Mechanics of Power slides cover the statistical framework for conducting power calculations.
This lecture offers practical guidance for researchers and practitioners to use when thinking about ethics in study design and implementation, and how to apply that framework in real-world settings.
Threats and Analysis
This lecture illustrates some of the challenges that can occur while conducting a randomized evaluation and how researchers can approach these challenges in the implementation and analysis phases.
- Threats and Analysis slides (2023)
Case studies illustrating how to analyze and interpret the results of a randomized evaluation in the presence of various threats to analysis, such as attrition, spillovers, and non-compliance:
How can results from one context inform policies in another? This lecture provides a framework for how to assess the applicability of evidence across contexts.
Last updated August 2023.
These resources are a collaborative effort. If you notice a bug or have a suggestion for additional content, please fill out this form.
We thank Therese David for thoughtful comments and suggestions. We also thank the Training teams past and present of all J-PAL offices for their assistance in creating these materials. Any errors are our own.