A framework for covariate balance using Bregman distances
From MaRDI portal
(Redirected from Publication:5152169)
Abstract: A common goal in observational research is to estimate marginal causal effects in the presence of confounding variables. One solution to this problem is to use the covariate distribution to weight the outcomes such that the data appear randomized. The propensity score is a natural quantity that arises in this setting. Propensity score weights have desirable asymptotic properties, but they often fail to adequately balance covariate data in finite samples. Empirical covariate balancing methods pose as an appealing alternative by exactly balancing the sample moments of the covariate distribution. With this objective in mind, we propose a framework for estimating balancing weights by solving a constrained convex program where the criterion function to be optimized is a Bregman distance. We then show that the different distances in this class render identical weights to those of other covariate balancing methods. A series of numerical studies are presented to demonstrate these similarities.
Recommendations
Cited in
(19)- Covariate balancing propensity score by tailored loss functions
- Network flow methods for the minimum covariate imbalance problem
- Entropy balancing for continuous treatments
- Covariates distributions balancing for continuous treatment
- Covariate association eliminating weights: a unified weighting framework for causal effect estimation
- Balancing covariates via propensity score weighting
- Testing for covariate balance using quantile regression and resampling methods
- Kernel balancing: a flexible non-parametric weighting procedure for estimating causal effects
- Minimal dispersion approximately balancing weights: asymptotic properties and practical considerations
- Stable weights that balance covariates for estimation with incomplete outcome data
- Covariate balancing propensity score
- Errata for “A framework for covariate balance using Bregman distances”
- Improving Trial Generalizability Using Observational Studies
- How Well Can Fine Balance Work for Covariate Balancing
- Transporting experimental results with entropy balancing
- A calibration approach to transportability and data-fusion with observational data
- Mahalanobis balancing: a multivariate perspective on approximate covariate balancing
- Covariate balancing with measurement error
- Propensity score weighting for causal inference with multiple treatments
This page was built for publication: A framework for covariate balance using Bregman distances
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5152169)
