Ressources pour la recherche aléatoire
J-PAL North America developed this pair of resources to support the use of nonpublic administrative data for randomized evaluations. The guide provides general tips on how to obtain and use these data. The catalog of key US data sets provides agency-specific information on how to request data.
This document provides an outline on how to approach collecting cost information, what costs to include and exclude, and how detailed cost data should be.
This step-by-step guide uses data and an annotated Stata do-file to illustrate how a simple randomization can be carried out using Stata.
IPA's data publication guideline covers the principles of organizing and documenting data and code – illustrated using examples from Stata – at all steps of the project lifecycle with the goal of making research reproducible.
The PPI is a leading household poverty measurement tool, used by more than 500 organizations around the world, to measure household poverty, improve targeting and social performance, and track changes in welfare. It is a country-specific ten-question scorecard that estimates whether a particular household is living below the poverty line.
This is an advanced, applied, Stata class. You should be quite comfortable using Stata. You are very familiar with the following concepts:
- Loops with varlist and numlist, as well as while loops
- The if command (distinct from the if qualifier)
- N and _n
You are likely somewhat familiar with:
- capture and assert
- Saved results such as r(N), r(levels
The Lessons of Administrative Data
A document that highlights examples of landmark studies made possible by administrative data.
Using Administrative Data for Randomized Evaluations
A guide that provides practical guidance on how to obtain and use nonpublic administrative data for a randomized evaluation.
Administrative Steps for Launching a Randomized Evaluation in the United States
A checklist that provides guidance on the logistical and administrative steps that are necessary to launch a randomized evaluation that adheres to legal regulations, follows transparency guidelines required by many academic journals, and complies with security procedures required by regulatory or ethical standards.
Administrative Data Poster
A poster that summarizes some of the key takeaways and visuals from the guide: Using Administrative Data for Randomized Evaluations.
Common Questions and Concerns about Randomized Evaluations
A two-page document that addresses concerns potential evaluators may have about the logistical, ethical, and financial implications of running a randomized evaluation.
The Danger of Underpowered Evaluations
A one-page document that highlights the risks associated with running an evaluation that is not designed to detect a meaningful impact of a program.