Yale
Tobin Center for Economic Policy
Search
Tobin Home
Journal Publication

Incorporating ethics and welfare into randomized experiments

Published: December 2020
Author(s): Yusuke Narita
Blue bins indicate ATE estimates for RCT, while transparent bins with red outlines indicate those for EXAM. The solid vertical line indicates the mean for EXAM, while the dashed vertical line indicates that for RCT.
Professor Narita analyzes the possibility of integrating ethics into randomized control trials, which are important experimental research tools that provide valuable insight into efficacy and can have lasting implications for research participants.

With an aim of improving welfare for subjects in RCTs, Professor Narita proposes a design for RCTs called "Experiment as Market," or "EXAM." EXAM produces a welfare-maximizing allocation of treatment-assignment probabilities and estimates causal effects similarly to traditional RCTs.

Abstract and Citation

Yusuke Narita. Incorporating ethics and welfare into randomized experiments. Proc Natl Acad Sci U S A. 2020 Dec 21;118(1):e2008740118. doi: 10.1073/pnas.2008740118.

Abstract

Randomized controlled trials (RCTs) enroll hundreds of millions of subjects and involve many human lives. To improve subjects’ welfare, I propose a design of RCTs that I call Experiment-as-Market (EXAM). EXAM produces a welfare-maximizing allocation of treatment-assignment probabilities, is almost incentive-compatible for preference elicitation, and unbiasedly estimates any causal effect estimable with standard RCTs. I quantify these properties by applying EXAM to a water-cleaning experiment in Kenya. In this empirical setting, compared to standard RCTs, EXAM improves subjects’ predicted well-being while reaching similar treatment-effect estimates with similar precision.

Publication Link
https://www.pnas.org/doi/full/10.1073/pnas.2008740118
Page Count
6