2012
DOI: 10.1093/pan/mpr013
|View full text |Cite
|
Sign up to set email alerts
|

Causal Inference without Balance Checking: Coarsened Exact Matching

Abstract: We discuss a method for improving causal inferences called ''Coarsened Exact Matching'' (CEM), and the new ''Monotonic Imbalance Bounding'' (MIB) class of matching methods from which CEM is derived. We summarize what is known about CEM and MIB, derive and illustrate several new desirable statistical properties of CEM, and then propose a variety of useful extensions. We show that CEM possesses a wide range of statistical properties not available in most other matching methods but is at the same time exceptional… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

8
1,990
0
11

Year Published

2014
2014
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 2,725 publications
(2,009 citation statements)
references
References 46 publications
8
1,990
0
11
Order By: Relevance
“…We included here phaco-trabectome patients, who have a different, mixed indication that often includes visually significant cataract as the primary motivator while presenting with a relatively stable glaucoma. We did so after demonstrating by a rigorous statistical matching method, coarsened exact matching 15 , that phacoemulsification does not contribute significantly to IOP reduction when done at the same time 9 or in a surgery prior to trabectome surgery 16 .…”
Section: Discussionmentioning
confidence: 99%
“…We included here phaco-trabectome patients, who have a different, mixed indication that often includes visually significant cataract as the primary motivator while presenting with a relatively stable glaucoma. We did so after demonstrating by a rigorous statistical matching method, coarsened exact matching 15 , that phacoemulsification does not contribute significantly to IOP reduction when done at the same time 9 or in a surgery prior to trabectome surgery 16 .…”
Section: Discussionmentioning
confidence: 99%
“…A new sample of online volunteers completed an identical study on empathy and morality between 2015 and 2017. We then apply an exact matching (Iacus, King, Porro, & Katz, 2012) algorithm to create a 2015-17 subsample that strongly mirrors our 2007-08 sample on the primary pre-treatment covariates, thus eliminating differences in age and other potentially confounding demographic measures. In conjunction with the correlation reported in Study 1, a difference between waves would point towards a cohort effect.…”
Section: Study 3: Time-lag Analysesmentioning
confidence: 99%
“…To this end, numerous methods for pre-processing observational data have been developed, whose general aim is to compensate for non-random assignment by either weighting or matching observations as a function of their covariate values. In our present case, given the large sample size and substantial overlap between waves on the primary demographic covariates, we were able to seek exact matches, using a coarsened exact matching algorithm (Ho, Imai, King, & Stuart, 2011;Iacus, King, Porro, & Katz, 2012).…”
Section: Imbalance Correctionmentioning
confidence: 99%
“…Using CEM before the implementation of the subsequent matching technique is suggested as an appropriate procedure that improves the quality of matching and the inferences drawn after PSM (Blackwell et al, 2009;Iacus et al, 2011).…”
Section: Methodsologymentioning
confidence: 99%
“…It meets the congruence principle and it restricts the matched data to areas of common empirical support (Iacus et al, 2011).…”
Section: Methodsologymentioning
confidence: 99%