10.6084/M9.FIGSHARE.15314645.V1
Xiaohong He
Xiaohong
He
Lei Wang
Lei
Wang
Ensemble and calibration multiply robust estimation for quantile treatment effect
<p>Quantile treatment effects can be important causal estimands in the evaluation of biomedical treatments or interventions for health outcomes such as birthweight and medical cost. However, the existing estimators require either a propensity score model or a conditional density vector model is correctly specified, which is difficult to verify in practice. In this paper, we allow multiple models for propensity score and conditional density vector, then construct a class of calibration estimators based on multiple imputation and inverse probability weighting approaches via empirical likelihood. The resulting estimators multiply robust in the sense that they are consistent if any one of these models is correctly specified. Moreover, we propose another class of ensemble estimators to reduce computational burden while ensuring multiple robustness. Simulations are performed to evaluate the finite sample performance of the proposed estimators. Two applications to the birthweight of infants born in the United States and AIDS Clinical Trials Group Protocol 175 data are also presented.</p>
Medicine
Neuroscience
Biotechnology
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Taylor & Francis
2021
2021-08-19
2024-02-09
Journal contribution
248206 Bytes
10.6084/m9.figshare.15314645
10.1080/02664763.2021.1966397
CC BY 4.0