Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use

Author(s)
Knittel, Christopher R; Stolper, Samuel
Thumbnail
DownloadPublished version (713.3Kb)
Publisher Policy
Terms of use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Metadata
Show full item record
Abstract
<jats:p> We use causal forests to evaluate the heterogeneous treatment effects (TEs) of repeated behavioral nudges toward household energy conservation. The average response to treatment is a monthly electricity reduction of 9 kilowatt-hours (kWh), but the full distribution of responses ranges from -40 to +10 kWh. Households learn to reduce more over time, conditional on having responded in year one. Pre-treatment consumption and home value are the most commonly used predictors in the forest. The results suggest the ability to use machine learning techniques for improved targeting and tailoring of treatment. </jats:p>
Date issued
2021
URI
https://hdl.handle.net/1721.1/144195
Department
Sloan School of Management
Journal
American Economic Association Papers and Proceedings
Publisher
American Economic Association
Citation
Knittel, Christopher R and Stolper, Samuel. 2021. "Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use." American Economic Association Papers and Proceedings, 111.
Version: Final published version
Collections