Summary and discussion of “ The central role of the propensity score in observational studies for causal effects

By Jessica J. Chemali, Michael Vespe. 2014

How researchers see this paper

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

In Causal Inference & Discovery

Citations in the corpus

Machine Learning Methods That Economists Should Know About (2019, methodology): “This type of approximation is used in economic applications in Ruiz et al. [2017] and Hartford et al.”
Tree-structured analysis of treatment effects with large observational data (2012, background): “When both those who received treatment and those who received control share the same propensity score within a terminal node of a tree, the inference of the treatment effect for this particular terminal node is unbiased due to the balancing property of the propensity score [10].”
Country-level institutions, firm value, and the role of corporate social responsibility initiatives (2017, methodology): “To address this concern, we randomize our sample by employing the propensity score matching method developed by Rosenbaum and Rubin (1983).”
New Evidence on the Finite Sample Properties of Propensity Score Reweighting and Matching Estimators (2014, methodology): “…of either covariates or propensity scores, 4 The dual assumptions of conditional independence and overlap are referred to as strongly ignorable by Rosenbaum and Rubin (1983). depending on the context.5 For propensity score-based estimators, we use an estimate of the propensity score rather…”
Locomotives of Local Growth: The Short- and Long-Term Impact of Railroads in Sweden (2017, methodology): “To mimic a more experimental setting we follow the evaluation literature and balance our sample on observables using propensity scores (Rosenbaum and Rubin 1983).”
Evaluating the Effectiveness of Correctional Education: A Meta-Analysis of Programs That Provide Education to Incarcerated Adults (2013, methodology): “However, the advantage of propensity score matching over a manual matching procedure is that it can help researchers obtain baseline equivalence over a much larger number of variables than one can typically achieve with a manual matching procedure (Rosenbaum and Rubin, 1983).”
Limitations of individual causal models, causal graphs, and ignorability assumptions, as illustrated by random confounding and design unfaithfulness (2015, background): “Independence of treatment A and the potential-outcome pair (Y1, Y0) is often called strong ignorability, complete (or full) exchangeability, or unconfoundedness in the preallocation distribution or treatment assignment, in which A is random [3, 26, 27].”
A Tutorial on Propensity Score Estimation for Multiple Treatments Using Generalized Boosted Models (2013, background): “Imbens [9] showed that condition 2 is sufficient for consistent estimation of t and that it is related to the ‘strong ignorability’ assumption of [29], which requires that treatment indicators be independent of the entire vector of potential outcomes.”
Regional Policy Evaluation: Interactive Fixed Effects and Synthetic Controls (2016, methodology): “It is well known since Rosenbaum and Rubin (1983) that conditions 1 and 2 imply the condition E(εit | Di = 1, p(xi, λi)) = 0, 8 The variance of the estimator can be computed using formulas in Bai (2003, 2009). in which the distinction between observed variables xi and unobserved variables λi does…”
Effective Macroprudential Policy: Cross‐Sector Substitution from Price and Quantity Measures (2016, unknown): “PSM was introduced in research on medicine (Rosenbaum and Rubin 1983) and it has since become popular in macroeconomics.”
Balancing Covariates via Propensity Score Weighting (2014, background): “The propensity score (Rosenbaum and Rubin 1983) is the probability of assignment to the treatment group given the covariates, e(x) = Pr(Zi = 1|Xi = x).”
Effectiveness and efficiency of SME innovation policy (2013, background): “But after matching the chances of employing graduates should 7 Rosenbaum and Rubin (1983) showed that matching enterprises on just the propensity score, rather than matching firms on the vector of characteristics of equation 2, was appropriate.”
A comparison of 12 algorithms for matching on the propensity score (2013, methodology): “There are four methods in which the propensity score can be used: matching on the propensity score, stratification on the propensity score, covariate adjustment using the propensity score, and inverse probability of treatment weighting using the propensity score [1, 2].”
Summary Report of the AAPOR Task Force on Non-probability Sampling (2013, methodology): “When used in this context, the propensity score is the conditional probability of receiving the treatment rather than the control given the observed covariates (Rosenbaum and Rubin 1983).”
Children's Antisocial Behavior, Mental Health, Drug Use, and Educational Performance After Parental Incarceration (2012, methodology): “Children with incarcerated parents and comparison children should be matched (for example, using propensity scores, Rosenbaum & Rubin, 1983) on a wide range of confounding variables that are measured before incarceration.”