Opiates for the Matches: Matching Methods for Causal Inference

By Jasjeet S. Sekhon. 2009

331 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/59bac42605545e0acc917d582971e4909c0660d8

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

Ebalance: A Stata Package for Entropy Balancing (2013, neutral): “…or propensity score techniques have become popular in the social sciences in recent years to preprocess data prior to the estimation of causal eﬀects in observational studies with binary treatments under the selection on observables assumption (Ho, Imai, King, and Stuart 2007; Sekhon 2009).”
Generalizing Experimental Findings (2015, background): “In many instances, generalizations can only be achieved by conditioning on posttreatment variables, an operation that is generally frowned upon in the potential outcomes framework (Rosenbaum, 2002, pp. 73–74; Rubin, 2004; Sekhon, 2009) but has become extremely useful in graphical analysis.”
Adjusting for Confounding with Text Matching (2020, background): “…assessing the suitability of our g function.6 Analysts should read 6Although matching has many strengths and is a popular approach (Ho et al. 2007; Sekhon 2009), we acknowledge that it lacks some matched documents to evaluate two potential points of failure: (1) the g function has obscured an…”
The Statistics of Causal Inference: A View from Political Methodology (2015, neutral): “See Sekhon (2009) and Arceneaux, Gerber, and Green (2006) for overviews of this confusion.”
Computational Social Science for the World Wide Web (CSSW3) (2016, methodology): “We will discuss diﬀerent methods (post-hoc control meth-ods like matching [3] and natural experiment [2]) for making causal inference based on organic data.”
When Less Is More: Effects of Grade Skipping on Adult STEM Productivity Among Mathematically Precocious Adolescents (2013, neutral): “…methods have been proposed recently (e.g., Diamond & Sekhon, in press; Iacus, King, & Porro, 2012; Ho, Imai, King, & Stuart, 2007; Imai, King, & Stuart, 2008; Sekhon, 2007, 2009), but we combine two popular, longstanding methods, exact and propensity score matching, to create matched samples.”
Adjusting treatment effect estimates by post‐stratification in randomized experiments (2013, methodology): “We match as described in Sekhon and Grieve (2011). We then consider each matched pair a single unit with two potential outcomes.”
Matching Methods in Practice: Three Examples (2015, methodology): “For general discussions of matching methods see Rosenbaum (1989), Rubin (1973a, 1979), Rubin and Thomas (1992ab), Sekhon (2009), and Hainmueller (2012).”
Newspaper Closures Polarize Voting Behavior (2018, background): “As such, covariate values which have no support among our closure set should not enter into our estimates, which the ATT estimator avoids (Sekhon 2009, 495).”