• Corpus ID: 239769301

Adjusting for Unobserved Confounding Using Large-Scale Propensity Scores

@inproceedings{Zhang2021AdjustingFU,
  title={Adjusting for Unobserved Confounding Using Large-Scale Propensity Scores},
  author={Linying Zhang and Yixin Wang and Martijn J. Schuemie and David M. Blei and George Hripcsak},
  year={2021}
}
Even though observational data contain an enormous number of covariates, the existence of unobserved confounders still cannot be excluded and remains a major barrier to drawing causal inference from observational data. A large-scale propensity score (LSPS) approach may adjust for unobserved confounders by including tens of thousands of available covariates that may be correlated with them. In this paper, we present conditions under which LSPS can remove bias due to unobserved confounders. In… 

Figures from this paper

References

SHOWING 1-10 OF 68 REFERENCES
Reducing Bias in Observational Studies Using Subclassification on the Propensity Score
Abstract The propensity score is the conditional probability of assignment to a particular treatment given a vector of observed covariates. Previous theoretical arguments have shown that
High-dimensional Propensity Score Adjustment in Studies of Treatment Effects Using Health Care Claims Data
TLDR
In typical pharmacoepidemiologic studies, the proposed high-dimensional propensity score resulted in improved effect estimates compared with adjustment limited to predefined covariates, when benchmarked against results expected from randomized trials.
Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder.
TLDR
This work shows that, with at least two independent proxy variables satisfying a certain rank condition, the causal effect is nonparametrically identified, even if the measurement error mechanism, i.e., the conditional distribution of the proxies given the confounder, may not be identified.
The central role of the propensity score in observational studies for causal effects
Abstract : The results of observational studies are often disputed because of nonrandom treatment assignment. For example, patients at greater risk may be overrepresented in some treatment group.
Invited commentary: understanding bias amplification.
  • J. Pearl
  • Psychology
    American journal of epidemiology
  • 2011
TLDR
This commentary sheds broader light on this comparison by considering the cumulative effects of conditioning on multiple covariates and showing that bias amplification may build up at a faster rate than bias reduction, and derives a partial order on sets of covariates which reveals preference for conditioning on outcome- related, rather than exposure-related, confounders.
Bias Amplification and Bias Unmasking
TLDR
This work identifies the fact that the popular approach of adding group fixed effects can lead to bias amplification as well and proposes a way to add bias decomposition information to graphical displays for sensitivity analysis to help practitioners think through the potential for bias amplification and bias unmasking in actual applications.
Instrumental variables as bias amplifiers with general outcome and confounding
TLDR
A general theory is provided, showing that the treatment‐outcome relationship is unconfounded conditional on the observed covariates under a wide class of models satisfying certain monotonicity assumptions.
The Mechanics of Omitted Variable Bias: Bias Amplification and Cancellation of Offsetting Biases
TLDR
Conditions under which adjusting for X increases OVB are discussed, and it is demonstrated that conditioning on X increases the imbalance in U, which turns U into an even stronger confounder, which shows that Conditioning on an unreliably measured confoundinger can remove more bias than the corresponding reliable measure.
An Introduction to Proximal Causal Learning
TLDR
A formal potential outcome framework for proximal causal learning is introduced, which while explicitly acknowledging covariate measurements as imperfect proxies of confounding mechanisms, offers an opportunity to learn about causal effects in settings where exchangeability on the basis of measured covariates fails.
Estimating Causal Effects from Large Data Sets Using Propensity Scores
TLDR
Propensity score methods generalize subclassification in the presence of many confounding covariates, such as age, region of the country, and sex, in a study of smoking and mortality.
...
1
2
3
4
5
...