Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use
<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...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
American Economic Association
2022
|
| Online Access: | https://hdl.handle.net/1721.1/144195 |
| _version_ | 1826213667024142336 |
|---|---|
| author | Knittel, Christopher R Stolper, Samuel |
| author2 | Sloan School of Management |
| author_facet | Sloan School of Management Knittel, Christopher R Stolper, Samuel |
| author_sort | Knittel, Christopher R |
| collection | MIT |
| description | <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> |
| first_indexed | 2024-09-23T15:52:54Z |
| format | Article |
| id | mit-1721.1/144195 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:52:54Z |
| publishDate | 2022 |
| publisher | American Economic Association |
| record_format | dspace |
| spelling | mit-1721.1/1441952023-01-11T20:06:15Z Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use Knittel, Christopher R Stolper, Samuel Sloan School of Management <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> 2022-08-03T16:12:35Z 2022-08-03T16:12:35Z 2021 2022-08-03T15:13:02Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/144195 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. en 10.1257/PANDP.20211090 American Economic Association Papers and Proceedings 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. application/pdf American Economic Association American Economic Association |
| spellingShingle | Knittel, Christopher R Stolper, Samuel Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use |
| title | Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use |
| title_full | Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use |
| title_fullStr | Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use |
| title_full_unstemmed | Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use |
| title_short | Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use |
| title_sort | machine learning about treatment effect heterogeneity the case of household energy use |
| url | https://hdl.handle.net/1721.1/144195 |
| work_keys_str_mv | AT knittelchristopherr machinelearningabouttreatmenteffectheterogeneitythecaseofhouseholdenergyuse AT stolpersamuel machinelearningabouttreatmenteffectheterogeneitythecaseofhouseholdenergyuse |