Working Paper: NBER ID: w26531
Authors: Christopher R. Knittel; Samuel Stolper
Abstract: We use causal forests to evaluate the heterogeneous treatment effects (TEs) of repeated behavioral nudges towards household energy conservation. The average response is a monthly electricity reduction of 9 kilowatt-hours (kWh), but the full distribution of responses ranges from -30 to +10 kWh. Selective targeting of treatment using the forest raises social net benefits by 12-120 percent, depending on the year and welfare function. Pre-treatment consumption and home value are the strongest predictors of treatment effect. We find suggestive evidence of a "boomerang effect": households with lower consumption than similar neighbors are the ones with positive TE estimates.
Keywords: Machine Learning; Energy Conservation; Causal Forests; Heterogeneous Treatment Effects
JEL Codes: C53; D90; Q40
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| pretreatment consumption (D12) | treatment response (C22) |
| home value (R31) | treatment response (C22) |
| lower consumption than neighbors (D12) | increased energy usage (Q41) |
| home energy reports (Q48) | reduced energy consumption (Q41) |