Title Using machine learning to target treatment : the case of household energy use / Christopher R. Knittel, Samuel Stolper

Published Cambridge, Mass. : National Bureau of Economic Research, 2019

Click on the following:
JSTOR Sustainability

Copies

Description 1 online resource (47 pages) : illustrations, map Series NBER working paper series ; no. 26531 Working paper series (National Bureau of Economic Research) ; no. 26531. Summary 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 Notes "December 2019." Bibliography Includes bibliographical references (pages 29-31) Notes Online resource; title from http://www.nber.org/papers/26531 viewed December 12, 2019 Subject Machine learning -- Econometric models Economics -- Research -- Methodology -- Econometric models Electric power -- Conservation -- United States -- Econometric models Dwellings -- Energy conservation -- United States -- Econometric models Energy conservation -- United States -- Econometric models Dwellings -- Energy conservation -- Econometric models. Energy conservation -- Econometric models. General. Forecasting and Prediction Methods Simulation Methods. United States. Form Electronic book Author Stolper, Samuel, author National Bureau of Economic Research, publisher.

  Permalink