External and Internal Validity of a Geographic Quasi-Experiment Embedded in a Cluster-Randomized Experiment

aUniversity of Maryland, College Park, MD, USA
bNBER, Cambridge, MA, USA
cWellesley College, Wellesley, MA, USA
dMicrosoft AI and Research, Redmond, WA, USA

Regression Discontinuity Designs

ISBN: 978-1-78714-390-6, eISBN: 978-1-78714-389-0

ISSN: 0731-9053

Publication date: 13 May 2017


This chapter analyzes a geographic quasi-experiment embedded in a cluster-randomized experiment in Honduras. In the experiment, average treatment effects of conditional cash transfers on school enrollment and child labor were large – especially in the poorest experimental blocks – and could be generalized to a policy-relevant population given the original sample selection criteria. In contrast, the geographic quasi-experiment yielded point estimates that, for two of three dependent variables, were attenuated. A judicious policy analyst without access to the experimental results might have provided misleading advice based on the magnitude of point estimates. We assessed two main explanations for the difference in point estimates, related to external and internal validity.



Galiani, S., McEwan, P. and Quistorff, B. (2017), "External and Internal Validity of a Geographic Quasi-Experiment Embedded in a Cluster-Randomized Experiment", Regression Discontinuity Designs (Advances in Econometrics, Vol. 38), Emerald Publishing Limited, pp. 195-236. https://doi.org/10.1108/S0731-905320170000038009

Download as .RIS



Emerald Publishing Limited

Copyright © 2017 Emerald Publishing Limited

Please note you might not have access to this content

You may be able to access this content by login via Shibboleth, Open Athens or with your Emerald account.
If you would like to contact us about accessing this content, click the button and fill out the form.