Algorithmic Nudges
How to cite
Misra, Sanjog. 2020. "Algorithmic Nudges." AEA RCT Registry. AEARCTR-0006660. https://doi.org/10.1257/rct.6660-1.0
Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.
* Primary investigator
Abstract
Nudges are a combination of words and contexts chosen by the sender to elicit a (desired) response from the receiver without a material change in incentives. We aim to develop and test a framework that algorithmically constructs individual nudges and test the value of this approach in the context of the SNAP program.
Intervention
The intervention involves the construction and sending of algorithmically targeted messages (via sms and email) to those SNAP participants who consented to receiving a reminder. The messages remind the participants that they need to fill out the SAR 7 update form to continue receiving SNAP benefits.
Experimental design
The experiment has four treatments arms:
(1) Control/Status Quo nudge decided by and used by Code for America
(2) Random (Random allocation of nudges derived from optimal design theory)
(3) Optimal (Model based optimal message - estimated using pilot data)
(4) Algorithmic (Model based targeted messages - estimated using pilot data)
Assignment to arms is random with 10%,10%, 30% and 50% to each of the arms listed above.
Design details
Cited by
No citation data available for this registration yet.