# Addressing Positivity Violations in Causal Effect Estimation using Gaussian Process Priors

@inproceedings{Zhu2021AddressingPV, title={Addressing Positivity Violations in Causal Effect Estimation using Gaussian Process Priors}, author={Yaqian Zhu and Nandita Mitra and Jason A Roy}, year={2021} }

In observational studies, causal inference relies on several key identifying assumptions. One identifiability condition is the positivity assumption, which requires the probability of treatment be bounded away from 0 and 1. That is, for every covariate combination, it should be possible to observe both treated and control subjects, i.e., the covariate distributions should overlap between treatment arms. If the positivity assumption is violated, population-level causal inference necessarily…

## Figures and Tables from this paper

## References

SHOWING 1-10 OF 34 REFERENCES

Diagnosing and responding to violations in the positivity assumption

- Mathematics, MedicineStatistical methods in medical research
- 2012

The positivity assumption is discussed in the context of assessing model and parameter-specific identifiability of causal effects and several approaches for improving the identifiable of parameters in the presence of positivity violations are reviewed.

Relaxed covariate overlap and margin-based causal effect estimation.

- Mathematics, MedicineStatistics in medicine
- 2018

A new balance-related condition involving the convex hulls of treatment groups, which I term relaxed covariate overlap is discussed, which can be linked to a concept from machine learning, termed the margin, which leads to an approach in which one can perform causal inference in a three-step manner.

Assessing Overlap in Covariate Distributions

- Mathematics
- 2015

INTRODUCTION When a researcher wishes to proceed to estimate causal effects under the assumption of unconfoundedness, there are various statistical methods that can be used to attempt to adjust for…

Overlap in observational studies with high-dimensional covariates

- Mathematics, Computer Science
- 2017

Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects (with Discussion)

- Computer Science, Mathematics
- 2020

It is impressive that the proposed Bayesian causal forest model, in many settings, has better bias reduction, more consistent 95% coverage probability and shorter uncertainty intervals compared to the vanilla BART, which boasts better performance in a host of modern causal inference studies.

ESTIMATING POPULATION AVERAGE CAUSAL EFFECTS IN THE PRESENCE OF NON-OVERLAP: THE EFFECT OF NATURAL GAS COMPRESSOR STATION EXPOSURE ON CANCER MORTALITY.

- Computer Science, MathematicsThe annals of applied statistics
- 2019

A flexible, data-driven definition of propensity score overlap and non-overlap regions is proposed and a novel Bayesian framework to estimate population average causal effects with minor model dependence and appropriately large uncertainties in the presence of non- overlap and causal effect heterogeneity is developed.

Assessing lack of common support in causal inference using bayesian nonparametrics: Implications for evaluating the effect of breastfeeding on children's cognitive outcomes

- Mathematics, Psychology
- 2013

Causal inference in observational studies typically requires making comparisons between groups that are dissimilar. For instance, researchers investigating the role of a prolonged duration of…

Estimating causal effects from epidemiological data

- MedicineJournal of Epidemiology and Community Health
- 2006

This article reviews a condition that permits the estimation of causal effects from observational data, and two methods—standardisation and inverse probability weighting—to estimate population causal effects under that condition.

Dealing with limited overlap in estimation of average treatment effects

- Mathematics
- 2009

Estimation of average treatment effects under unconfounded or ignorable treatment assignment is often hampered by lack of overlap in the covariate distributions between treatment groups. This lack of…

The central role of the propensity score in observational studies for causal effects

- Mathematics, Business
- 1983

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.…