Local Balance with Calibration using neural networks creates propensity score weights that enforce local covariate balance and calibration, yielding more stable weights and lower bias in average treatment effect estimates than prior nonparametric approaches.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Local Balance Calibration for Nonparametric Propensity Score Estimation
Local Balance with Calibration using neural networks creates propensity score weights that enforce local covariate balance and calibration, yielding more stable weights and lower bias in average treatment effect estimates than prior nonparametric approaches.