A0990
Title: Double machine learning for nonresponse in surveys
Authors: Mehdi Dagdoug - McGill University (Canada) [presenting]
David Haziza - University of Ottawa (Canada)
Abstract: Predictive models are increasingly integrated into survey strategies, supporting tasks such as model-based estimation, model-assisted estimation, and the treatment of nonresponse through imputation and reweighting. In recent decades, the rise of statistical learning has provided survey statisticians with highly flexible new tools alongside new theoretical and computational advancements. However, incorporating statistical learning into survey estimation poses challenges for conducting valid inference. An extension of the double machine learning framework is proposed for survey sampling, focusing on the treatment of nonresponse through augmented inverse probability weighting (AIPW) estimators. It is established that the resulting AIPW estimators are square-root n consistent and asymptotically normal under realistic rate conditions on the statistical learning algorithms. A consistent variance estimator is further proposed, enabling the construction of asymptotically valid confidence intervals. Issues related to model selection and aggregation will also be discussed. Simulation studies demonstrating the strong performance of the proposed methods will be presented.
