Examining the Efficacy of Coarsen Exact Matching as an Alternative to Propensity Score Matching
Fei Wan
TL;DR
This paper questions the view that coarsened exact matching (CEM) is a superior alternative to propensity score matching (PSM) for observational causal inference. Using a formal potential outcomes framework, it compares PSM and CEM across covariate balance, model dependence, and bias, employing simulations that vary covariate dimensionality and treatment prevalence. The results show that PSM generally yields better balance under multivariate standardized mean differences and is more robust to model misspecification, while CEM's inexact matching introduces systematic imbalance and data loss as dimensionality increases, unless coarsening is excessive and residual confounding grows. The study concludes that CEM is not a viable substitute for PSM when matching on many covariates, though PSM itself relies on valid balancing and ignorability assumptions and remains susceptible to unmeasured confounding; practitioners should consider the trade-offs and potential alternatives like weighting. Overall, PSM offers more reliable protection against model dependence and bias in high-dimensional settings and should be preferred over CEM for large covariate sets.
Abstract
Coarsened exact matching (CEM) is often promoted as a superior alternative to propensity score matching (PSM) for addressing imbalance, model dependence, bias, and efficiency. However, this recommendation remains uncertain. First, CEM is commonly mischaracterized as exact matching, despite relying on coarsened rather than original variables. This inexactness in matching introduces residual confounding, which necessitates accurate modeling of the outcome-confounder relationship post-matching to mitigate bias, thereby increasing vulnerability to model misspecification. Second, prior studies overlook that any imbalance between treated and untreated subjects matched on the same propensity score is attributable to random variation. Thus, claims that CEM outperforms PSM in reducing imbalance are unfounded, particularly when using metrics like Mahalanobis distance, which do not account for chance imbalance in PSM. Our simulations show that PSM reduces imbalance more effectively than CEM when evaluated with multivariate standardized mean differences (SMD), and unadjusted analyses indicate greater bias with CEM. While adjusted analyses in both CEM with autocoarsening and PSM may perform similarly when matching on few variables, CEM suffers from the curse of dimensionality as the number of factors increases, resulting in substantial data loss and unstable estimates. Increasing the level of coarsening may mitigate data loss but exacerbates residual confounding and model dependence. In contrast, both analytical results and simulations demonstrate that PSM is more robust to model misspecification and thus less model-dependent. Therefore, CEM is not a viable alternative to PSM when matching on a large number of covariates.