• Corpus ID: 248986274

Bias-robust Integration of Observational and Experimental Estimators

  title={Bias-robust Integration of Observational and Experimental Estimators},
  author={Michael Oberst and Alexander D'Amour and Minmin Chen and Yuyan Wang and David A. Sontag and Steve Yadlowsky},
We describe a simple approach for combining an unbiased and a (possibly) biased estimator, and demonstrate its robustness to bias: estimate the error and cross-correlation of each estimator, and use these to construct a weighted combination that minimizes mean-squared error (MSE). Theoretically, we demonstrate that for any amount of (unknown) bias, the MSE of the resulting estimator is bounded by a small multiple of the MSE of the unbiased estimator. In simulation, we demonstrate that when the… 

Figures and Tables from this paper


Combining Observational and Experimental Datasets Using Shrinkage Estimators
This work proposes a generic procedure for deriving shrinkage estimators in this setting, making use of a generalized unbiased risk estimate, and develops two new estimators that prove finite sample conditions under which they have lower risk than an estimator using only experimental data, and show that each achieves a notion of asymptotic optimality.
Minimax Rates and Adaptivity in Combining Experimental and Observational Data
This paper theoretically characterize the potential efficiency gain of integrating observational data into the RCT-based analysis from a minimax point of view, and proposes a fully adaptive anchored thresholding estimator that attains the optimal rate up to poly-log factors.
A Review of Generalizability and Transportability
When assessing causal effects, determining the target population to which the results are intended to generalize is a critical decision. Randomized and observational studies each have strengths and
Combining Multiple Observational Data Sources to Estimate Causal Effects
  • Shu Yang, P. Ding
  • Mathematics
    Journal of the American Statistical Association
  • 2020
This framework applies to asymptotically normal estimators, including the commonly used regression imputation, weighting, and matching estimator, and does not require a correct specification of the model relating the unmeasured confounders to the observed variables.
The Surrogate Index: Combining Short-Term Proxies to Estimate Long-Term Treatment Effects More Rapidly and Precisely
A common challenge in estimating the long-term impacts of treatments (e.g., job training programs) is that the outcomes of interest (e.g., lifetime earnings) are observed with a long delay. We
Elastic Integrative Analysis of Randomized Trial and Real-World Data for Treatment Heterogeneity Estimation
This work proposes a test-based elastic integrative analysis of the RT and RW data for accurate and robust estimation of the heterogeneity of treatment effect (HTE), which lies at the heart of precision medicine.
Extending inferences from a randomized trial to a new target population
This tutorial considers methods for extending causal inferences about time‐fixed treatments from a trial to a new target population of nonparticipants, using data from a completed randomized trial and baseline covariates from a sample from the target population.
On minimax estimation of a normal mean vector for general quadratic loss
Let X ~ ??(T,S>) (S known) and consider the problem of estimating the mean vector when loss is general quadratic loss (d ? 9)'Q(6 ? T). Many results are known for the case S = Q = I. There is also a
Observational studies.
Clinicians and researchers should be familiar with observational studies so they may better evaluate a proposed causal relationship and the quality of reports claiming such relationships, and determine if the findings are valid and applicable to their patient population.
The Combination of Forecasts
Two separate sets of forecasts of airline passenger data have been combined to form a composite set of forecasts. The main conclusion is that the composite set of forecasts can yield lower