Central Bank Communication, Conversational AI, and Macroeconomic Expectations

Last registered on June 15, 2026
View Trial History

Pre-Trial

Trial Information

General Information

Title
Central Bank Communication, Conversational AI, and Macroeconomic Expectations
RCT ID
AEARCTR-0018842
Initial registration date
June 07, 2026

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
June 15, 2026, 1:51 PM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Name
Wei Pin
Affiliation
ETH Zurich
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Elliott Ash
PI Affiliation
ETH Zurich
Contact Investigator
PI Name
Lena Song
PI Affiliation
University of Illinois Urbana-Champaign
Contact Investigator
PI Name
Michael Weber
PI Affiliation
Purdue University
Contact Investigator
PI Name
Shihan Xie
PI Affiliation
University of Illinois Urbana-Champaign
Contact Investigator

Additional Trial Information

Status
In development
Start date
2026-06-08
End date
2026-12-31
Keywords
Behavior
Additional Keywords
Macroeconomics, Monetary Policy, Artificial Intelligence
JEL code(s)
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
In this project, we examine whether AI chatbot–based monetary policy information treatments shift households' macroeconomic expectations and improve economic reasoning about interest-rate transmission channels. We conduct an online survey experiment on Prolific, randomly assigning approximately 3,000 U.S. participants to receive either a hawkish or dovish narrative regarding the monetary policy orientation of new Federal Reserve Chair Kevin Warsh, delivered through an AI chatbot interface, with participants randomized to either a minimal single-exchange interaction (control) or a structured two-phase conversational protocol (treatment) powered by Claude Sonnet 4.5. We will evaluate treatment effects on macroeconomic expectations and policy reasoning elicited through survey responses.
External Link(s)

Registration Citation

Citation
Ash, Elliott et al. 2026. "Central Bank Communication, Conversational AI, and Macroeconomic Expectations." AEA RCT Registry. June 15. https://doi.org/10.1257/rct.18842-1.0
Sponsors & Partners
Experimental Details

Interventions

Intervention(s)
Intervention Start Date
2026-06-08
Intervention End Date
2026-08-08

Primary Outcomes

Primary Outcomes (end points)
Short-run interest rate expectation, short-run inflation expectations, long-run macroeconomic forecasts, Federal Reserve dual mandate, out-of-domain interest rate prediction.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Economic uncertainty, perceived goal of the Federal Reserve, trust in the Federal Reserve, Federal Reserve political affiliation, out-of-domain policy reasoning, channel reasoning
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
We will recruit around 3,000 participants who completed prior waves of our recurring weekly survey from Prolific.

The survey begins with a screener and informed consent, followed by baseline measures of knowledge on economics and the Fed, attitudes towards AI, and attention checks.

We cross-randomizes the narrative framing of Kevin Warsh's monetary policy orientation and the delivery mode in a 2X2 between-subject design. Participants receive either a hawkish or dovish narrative regarding the monetary policy orientation of new Federal Reserve Chair Kevin Warsh, delivered through an AI chatbot interface, with participants randomized to either a minimal single-exchange interaction (Active Control) or a structured two-phase conversational protocol (Treatment). That is, the participants are randomized into four groups: (i) Active Control + Hawkish Narrative (ii) Active Control + Dovish Narrative (iii) Treatment + Hawkish Narrative (iv) Treatment + Dovish Narrative.

After exposure, participants complete a set of post-treatment measures.
Experimental Design Details
Not available
Randomization Method
Randomization within the chatbot.
Randomization Unit
Individual
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
ca. 3000 online survey participants
Sample size: planned number of observations
ca. 3000 online survey participants
Sample size (or number of clusters) by treatment arms
The participants are randomized into four groups: (i) Active Control + Hawkish Narrative (1/6) (ii) Active Control + Dovish Narrative (1/6) (iii) Treatment + Hawkish Narrative (1/3) (iv) Treatment + Dovish Narrative (1/3).
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Supporting Documents and Materials
IRB

Institutional Review Boards (IRBs)

IRB Name
University of Illinois Urbana-Champaign IRB
IRB Approval Date
2026-06-01
IRB Approval Number
IRB26-0678
Analysis Plan

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information