Full Matching in an Observational Study of Coaching for the SAT

By Ben B. Hansen. 2004

643 citations recorded by the source corpus.

Subfields: Economics and Econometrics, General Decision Sciences, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/2261d64e686cbf1c1b0970e1f8bdd228981958af

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 General Decision Sciences

In Statistics and Probability

Citations in the corpus

Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference (2007, background): “A useful alternative is ‘‘full matching,’’ which offers variable numbers of matches in each subclass (Hansen 2004).”
The Neyman— Rubin Model of Causal Inference and Estimation Via Matching Methods (2008, background): “Alternatively one can do optimal full matching (Hansen 2004; Rosenbaum 1991) instead of the greedy matching.”
A Primer on Propensity Score Analysis (2010, background): “Better still is full matching.(23,25) Matched sets are created that may contain multiple treatment or multiple comparison participants, or both.”
Why Propensity Scores Should Not Be Used for Matching (2019, background): “Optimal matching is usually preferred to greedy (Hansen, 2004); similarly, j-to-k matching (with j and k varying over units), or matching with replacement, are usually preferred to one-to-one matching.”
A Martingale Representation for Matching Estimators (2012, methodology): “(2) Many other matching schemes are possible (see, e.g., Gu and Rosenbaum 1993; Rosenbaum 2002; Hansen 2004; Iacus, King, and Porro 2009; Diamond and Sekhon 2010), and the results in this article are of broad generality.”
Improving Social Well-Being Through New Democratic Institutions (2014, methodology): “…observations of municipalities that adopted PB (the treatment) with a control group of observations of municipalities that are very similar to the treatment group in terms of population size, wealth, political inclinations, and geographic locations, but that did not adopt PB as in Hansen (2004).”
An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies (2011, background): “Full matching (Gu & Rosenbaum, 1993; Hansen, 2004; Rosenbaum, 1991) involves forming matched sets consisting of either one treated subject and at least one untreated subject or one untreated subject and at least one treated subject.”
Optimal Multilevel Matching in Clustered Observational Studies: A Case Study of the School Voucher System in Chile (2014, methodology): “We use a test statistic from Hansen et al. (2014) that provides inferences for students in schools within this framework.”
Attributing Effects to a Cluster-Randomized Get-Out-the-Vote Campaign (2009, background): “(1996); Rosenstone and Hansen (1993); Highton and Wolfinger (2001); Wolfinger and Rosenstone (1980), among many others — imbalance on age is particularly troubling.”
Patterns of Gendered Performance Differences in Large Introductory Courses at Five Research Universities (2017, methodology): “The matching model included the same factors as the regression model and relies on propensity scores for matching cases and controls (Hansen, 2004, 2007).”
Misunderstandings between experimentalists and observationalists about causal inference (2008, background): “Other options include higher order moments than the mean, nonparametric density plots, and propensity score summary statistics (Austin and Mamdani, 2006; Hansen, 2004; Rubin, 2001).”
Practice of Epidemiology Propensity Score Methods for Analyzing Observational Data Like Randomized Experiments: Challenges and Solutions for Rare Outcomes and Exposures (2015, background): “Greedy matching, by contrast, selects 1 exposed child at a time and finds the closest available match (22).”
An introduction to propensity-score methods for reducing confounding in observational studies (2011, positive): “Full matching (Gu & Rosenbaum, 1993; Hansen, 2004; Rosenbaum, 1991) involves forming matched sets consisting of either one treated subject and at least one untreated subject or one untreated subject and at least one treated subject.”