Subgroup balancing propensity score

Jing, Dong; Zhang, Junni L.; Zeng, Shuxi; Li, Fan

doi:10.1177/0962280219870836

Cited by 38 publications

(40 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, subgroup analysis is routinely conducted in randomized trials to examine whether the treatment effect depends on certain sets of patient characteristics 48 . For the same reason of transparency, it would be natural to develop propensity score weighting estimators for subgroup‐specific treatment effects 49,50 . Because the sample size of each subgroup may be limited, it is of particular interest to study whether OW is also effective in improving the efficiency in this context.…”

Section: Discussionmentioning

confidence: 99%

Propensity score weighting for covariate adjustment in randomized clinical trials

Zeng

Wang

2020

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

Chance imbalance in baseline characteristics is common in randomized clinical trials. Regression adjustment such as the analysis of covariance (ANCOVA) is often used to account for imbalance and increase precision of the treatment effect estimate. An objective alternative is through inverse probability weighting (IPW) of the propensity scores. Although IPW and ANCOVA are asymptotically equivalent, the former may demonstrate inferior performance in finite samples. In this article, we point out that IPW is a special case of the general class of balancing weights, and advocate to use overlap weighting (OW) for covariate adjustment. The OW method has a unique advantage of completely removing chance imbalance when the propensity score is estimated by logistic regression. We show that the OW estimator attains the same semiparametric variance lower bound as the most efficient ANCOVA estimator and the IPW estimator for a continuous outcome, and derive closed‐form variance estimators for OW when estimating additive and ratio estimands. Through extensive simulations, we demonstrate OW consistently outperforms IPW in finite samples and improves the efficiency over ANCOVA and augmented IPW when the degree of treatment effect heterogeneity is moderate or when the outcome model is incorrectly specified. We apply the proposed OW estimator to the Best Apnea Interventions for Research (BestAIR) randomized trial to evaluate the effect of continuous positive airway pressure on patient health outcomes. All the discussed propensity score weighting methods are implemented in the R package PSweight.

show abstract

Section: Discussionmentioning

confidence: 99%

Propensity score weighting for covariate adjustment in randomized clinical trials

Zeng

Wang

2020

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…While balancing the true propensity score would balance the covariates in all covariate-defined subgroups in expectation, the estimated weightsŵ i based on an estimated propensity score often fail to achieve covariate balance, particularly within subgroups. 16 As we show in Section 3, covariate balance in the subgroups is crucial for unbiased estimation of the S-WATE. Therefore, it is beneficial to choose weights that guarantee balance.…”

Section: 2mentioning

confidence: 91%

“…[10][11][12][13][14] However, causal inference methods for SGA with observational data remain underdeveloped. [15][16][17] In the context of ATE, covariate balance has been shown to be crucial to unbiased estimation of causal effects. 18,19 Propensity score methods 20 are the most popular method for achieving covariate balance, but have seldom been discussed in SGA.…”

Section: Introductionmentioning

confidence: 99%

Propensity score weighting for causal subgroup analysis

Yang

Lorenzi

Papadogeorgou

et al. 2021

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

A common goal in comparative effectiveness research is to estimate treatment effects on prespecified subpopulations of patients. Though widely used in medical research, causal inference methods for such subgroup analysis (SGA) remain underdeveloped, particularly in observational studies. In this article, we develop a suite of analytical methods and visualization tools for causal SGA.First, we introduce the estimand of subgroup weighted average treatment effect and provide the corresponding propensity score weighting estimator. We show that balancing covariates within a subgroup bounds the bias of the estimator of subgroup causal effects. Second, we propose to use the overlap weighting (OW) method to achieve exact balance within subgroups. We further propose a method that combines OW and LASSO, to balance the bias-variance tradeoff in SGA. Finally, we design a new diagnostic graph-the Connect-S plot-for visualizing the subgroup covariate balance. Extensive simulation studies are presented to compare the proposed method with several existing methods. We apply the proposed methods to the patient-centered results for uterine fibroids (COMPARE-UF) registry data to evaluate alternative management options for uterine fibroids for relief of symptoms and quality of life.

show abstract

“…Logistic regression was performed in the same pseudo-populations for odds ratios (ORs) of all-cause mortality outcomes within 30 days of COVID-19 infection. To further investigate the association among different age, sex, and racial/ethnic subgroups, subgroup specific IPTW methods were applied [ 10 ].…”

Section: Methodsmentioning

confidence: 99%

COVID-19 morbidity and mortality associated with angiotensin-converting enzyme inhibitors or angiotensin receptor blockers use among 14,129 patients with hypertension from a US integrated healthcare system

An¹,

Zhou²,

Wei³

et al. 2021

International Journal of Cardiology Hypertension

View full text Add to dashboard Cite

Objective Although recent evidence suggests no increased risk of severe COVID-19 outcomes associated with angiotensin-converting enzyme inhibitors (ACEIs) or angiotensin receptor blockers (ARBs) use, the relationship is less clear among patients with hypertension and diverse racial/ethnic groups. This study evaluates the risk of hospitalization and mortality among patients with hypertension and COVID-19 in a large US integrated healthcare system. Methods Patients with hypertension and COVID-19 (between March 1- September 1, 2020) on ACEIs or ARBs were compared with patients on other frequently used antihypertensive medications. Results Among 14,129 patients with hypertension and COVID-19 infection (mean age 60 years, 48% men, 58% Hispanic), 21% were admitted to the hospital within 30 days of COVID-19 infection. Of the hospitalized patients, 24% were admitted to intensive care units, 17% required mechanical ventilation, and 10% died within 30 days of COVID-19 infection. Exposure to ACEIs or ARBs prior to COVID-19 infection was not associated with an increased risk of hospitalization or all-cause mortality (rate ratios for ACEIs vs other antihypertensive medications = 0.98, 95% CI: 0.88, 1.08; ARBs vs others = 1.00, 95% CI: 0.90, 1.11) after applying inverse probability of treatment weights. These associations were consistent across racial/ethnic groups. Use of ACEIs or ARBs during hospitalization was associated with a lower risk of all-cause mortality (odds ratios for ACEIs or ARBs vs others = 0.50, 95% CI: 0.34, 0.72). Conclusion Our study findings support continuation of ACEI or ARB use for patients with hypertension during the COVID-19 pandemic and after COVID-19 infection.

show abstract

Subgroup balancing propensity score

Cited by 38 publications

References 32 publications

Propensity score weighting for covariate adjustment in randomized clinical trials

Propensity score weighting for covariate adjustment in randomized clinical trials

Propensity score weighting for causal subgroup analysis

COVID-19 morbidity and mortality associated with angiotensin-converting enzyme inhibitors or angiotensin receptor blockers use among 14,129 patients with hypertension from a US integrated healthcare system

Contact Info

Product

Resources

About