Robust Estimation of Risk Preferences

How to cite

Lucia, Aldo; Kobayashi, Shunto. 2023. "Robust Estimation of Risk Preferences." AEA RCT Registry. AEARCTR-0011749. https://doi.org/10.1257/rct.11749-1.1

Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.

Aldo Lucia* , Shunto Kobayashi

* Primary investigator

Registry ID
AEARCTR-0011749
DOI
https://doi.org/10.1257/rct.11749-1.1
First registered
Last updated
Status
Completed
Trial dates
2023-07-26 – 2023-07-30
Countries
United States of America ()
Registry record
http://www.socialscienceregistry.org/trials/11749

Abstract

Obtaining quantitative measures of risk preferences is important because it enables researchers to formulate predictions. However, the stringent assumptions on which these predictions rely often raise concerns about external validity: can these estimated models produce reliable predictions beyond the specific settings from which they were derived? In this paper, we study preferences under risk that may deviate from Expected Utility (EU) by relaxing its fundamental and most disputed assumption: the independence axiom. Rather than committing to a specific non-EU model, we estimate the set of utility functions that characterize the largest subrelation of a preference that satisfies the independence axiom. Without making further assumptions on preferences, this approach allows us to predict choices between two lotteries when one lottery is better for all utilities.

We will conduct an experiment on choices under risk, testing whether predictions generated with our approach, despite being less granular, are more accurate out-of-sample than those obtained with specific economic models or machine learning algorithms.

Experimental design

We run an online experiment on Prolific in which subjects make choices over monetary lotteries in two different blocks. In Block 1, we study together two prominent deviations from Expected Utility: the common ratio effect and preferences for randomization. In Block 2, we elicit certainty equivalents. We refer to the analysis plan for a detailed description of our experimental design.

Design details

Randomization method
Randomization is done by the computer server that hosts our experiment.
Randomization unit
Each subject completes 102 choice tasks from Block 1 and 33 choice tasks from Block 2. Subjects always complete the 102 choice tasks from Block 1 first, which are presented to them in a randomized order. Next, they face 33 choice tasks from Block 2, which are presented to them in a fixed order.
Clusters
500 subjects, 135 observations (binary choice tasks) for each subject
Observations
500 subjects, 135 observations (binary choice tasks) for each subject
Arms
All subjects face the same choice tasks.
Primary outcomes
Deterministic and probabilistic measures of accuracy in the predictions of choices between lotteries. We refer to the analysis plan for a detailed descriptions of the key outcome of interests.

Cited by

No citation data available for this registration yet.

Keywords