Using randomization in development economics research: a toolkit

Using randomization in development economics research: a toolkit

A guide to using randomised evaluation methods to overcome selection bias

This paper is a practical guide for researchers, students and practitioners in development economics wishing to introduce randomisation as part of a research design in the field.

It first covers the rationale for the use of randomisation, as a solution to selection bias and a partial solution to publication biases. The paper then discusses:

  • ways in which randomisation can be practically introduced in field settings
  • design issues such as sample size requirements, stratification, level of randomisation and data collection methods
  • analysing data from randomised evaluations when there are departures from the basic framework - in particular how to handle imperfect compliance and externalities
  • issues involved in drawing general conclusions from randomised evaluations, including the necessary use of theory as a guide when designing evaluations and interpreting results.

[adapted from author]