Cityscape: Volume 19 Number 2 | Use of Genetic Matching in Program Evaluation: The Case of RAD

Use of Genetic Matching in Program Evaluation: The Case of RAD

David Ruiz
Dennis Stout
Christine Herlihy
Econometrica

Evaluation Tradecraft
Evaluation Tradecraft presents short articles about the art of evaluation in housing and urban research. Through this department of Cityscape, the Office of Policy Development and Research presents developments in the art of evaluation that might not be described in detail in published evaluations. Researchers often describe what they did and what their results were, but they might not give readers a step-by-step guide for implementing their methods. This department pulls back the curtain and shows readers exactly how program evaluation is done. If you have an idea for an article of about 3,000 words on a particular evaluation method or an interesting development in the art of evaluation, please send a one-paragraph abstract to marina.l.myhre@hud.gov.

In this article, we describe the use of genetic matching in program evaluation, define cases in which this approach would be appropriate, and detail the value that this approach can provide. In particular, we focus on how the researchers used genetic matching in the ongoing evaluation of the Rental Assistance Demonstration (RAD) program, the results they obtained, and how they assessed its success. Clinical researchers and social scientists have developed genetic matching as a sampling technique for conducting nonrandomized observational studies in a quasi-experimental fashion. The method matches each member of the treatment group with one or more members of the control group. The match uses a set of key covariates, which the analyst selects based on prior expectations about possible treatment group participation factors. In the RAD evaluation, the research staff used stratified random sampling to select the RAD project sample (treatment group) from the participating RAD population. For the non-RAD sample (control group), researchers used a genetic matching algorithm to select a matched group of non-RAD public housing projects from the nonparticipating public housing population. Postsampling analysis confirmed that, on covariates likely to impact participation in RAD, the control group and the treatment group were similarly distributed. This matching technique can be a useful tool in program evaluation when membership in the treatment or control group is not random; for instance, if participation is voluntary, as is the case in the RAD program.


Previous Article   |   Next Article