A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: a Monte Carlo study

By Peter C. Austin, Paul Grootendorst, G. Anderson. Statistics in Medicine, 2007

1,147 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/4681ffb3c746faafb131f65da5fee0ea05203e3f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies (2015, methodology): “Diagnostics have been developed for stratification on the propensity score [2,7,8], matching on the propensity score [9, 10], and covariate adjustment using the propensity score [11].”
The use of propensity score methods with survival or time-to-event outcomes: reporting measures of effect similar to those used in randomized experiments (2013, methodology): “A simulation study found that this approach to variable selection worked very well in the context of propensity score matching [24].”
A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003 (2008, background): “The issue of variable selection for the propensity-score model has recently been examined [80].”
Estimating Response-Maximized Decision Rules With Applications to Breastfeeding (2009, background): “…both the response and the treatments and all variables that are causes only of response improve the performance of the treatment effect estimators (Austin, Grootendorst, and Anderson 2006; Judkins et al. 2006; Brookhart et al. 2006; Brookhart and van der Laan 2006; Lefebvre, Delaney, and Platt…”
Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples (2009, background): “2 of the standard deviation of the logit of the propensity score [3, 17, 18].”
Challenges With Propensity Score Strategies in a High-Dimensional Setting and a Potential Alternative (2011, methodology): “Stepwise regression used to be suggested as a strategy to deal with large numbers of covariates in this setting; this has been shown to be problematic as well (see, eg, Austin, Grootendorst, & Anderson, 2007 ) because this strategy differentially favors covariates that strongly predict the treatmen”
Assessing the Effectiveness of a College Freshman Seminar Using Propensity Score Adjustments (2011, background): “Covariates that are not related to selection into conditions are already balanced across treatment conditions and those that are not related to the outcome are not directly influencing it ( Austin et al. 2007 ).”
Prognostic score–based balance measures for propensity score methods in comparative effectiveness research (2013, positive): “The structure of the larger simulation study was adapted from Austin [6] and Belitser et al. [20].”
The performance of different propensity score methods for estimating marginal hazard ratios (2007, methodology): “We selected this approach to variable selection for the propensity score model, as it has been shown to result in better estimation compared with selecting only those variables that affect treatment selection [25].”
Antipsychotic Drug Use and Mortality in Older Adults with Dementia (2007, background): “Recent studies provide guidance on the selection of variables to include in the propensity score (25, 26).”
Using the Standardized Difference to Compare the Prevalence of a Binary Variable Between Two Groups in Observational Research (2009, background): “Several authors have proposed that standardized differences be used to compare the balance of baseline covariates between treatment groups (Austin, 2007, 2008a; Austin and Mamdani, 2006; Austin et al., 2007; Flury and Riedwyl, 1986; Ho et al., 2007).”
A comparison of 12 algorithms for matching on the propensity score (2013, methodology): “We selected this approach as it has been shown to result in superior performance compared with including all measured covariates or those variables that affect treatment selection [17].”
An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies (2011, methodology): “Several studies have demonstrated that propensity score matching eliminates a greater proportion of the systematic differences in baseline characteristics between treated and untreated subjects than does stratification on the propensity score or covariate adjustment using the propensity score ( Aust”