A1217
Title: Variable selection and estimation for the average treatment effect with error-prone confounders
Authors: Grace Yi - University of Western Ontario (Canada)
Li-Pang Chen - National Chengchi University (Taiwan) [presenting]
Abstract: In the causal inference framework, the inverse-probability-weighting estimation method and its variants have been commonly employed to estimate the average treatment effect. Such methods, however, are challenged by the presence of irrelevant pre-treatment variables and measurement errors. Ignoring these features and naively applying the usual inverse probability-weighting estimation procedures may typically yield biased inference results. An inference method is developed for estimating the average treatment effect with those features considered. Theoretical properties are established for the resulting estimator, and numerical studies are carried out to assess the finite sample performance of the proposed estimator.
