Matching Methods in Practice: Three Examples
Open accessThe DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Abstract
There is a large theoretical literature on methods for estimating causal effects under unconfoundedness, exogeneity, or selection-on-observables type assumptions using matching or propensity score methods. Much of this literature is highly technical and has not made inroads into empirical practice where many researchers continue to use simple methods such as ordinary least squares regression even in settings where those methods do not have attractive properties. In this paper, I discuss some of the lessons for practice from the theoretical literature and provide detailed recommendations on what to do. I illustrate the recommendations with three detailed applications.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482
The central role of the propensity score in observational studies for causal effects
ROSENBAUM, P. R., & RUBIN, D. B. (1983) · Biometrika · doi:10.1093/biomet/70.1.41 · Cited by 31,241
Estimating causal effects of treatments in randomized and nonrandomized studies
Rubin, D. B. (1974) · Journal of Educational Psychology · doi:10.1037/h0037350 · Cited by 9,436 · cited 1×
“The set up used in the current paper is by now the standard one in this literature, using the potential outcome framework for causal inference that builds on Fisher (1925) and Neyman (1923) and was extended to observational studies by Rubin (1974).”
MethodSOME PRACTICAL GUIDANCE FOR THE IMPLEMENTATION OF PROPENSITY SCORE MATCHING
Caliendo, M., & Kopeinig, S. (2008) · Journal of Economic Surveys · doi:10.1111/j.1467-6419.2007.00527.x · Cited by 6,238
Hainmueller, J. (2012) · Political Analysis · doi:10.1093/pan/mpr025 · Cited by 6,026
The Central Role of the Propensity Score in Observational Studies for Causal Effects
Rosenbaum, P. R., & Rubin, D. B. (1983) · Biometrika · doi:10.2307/2335942 · Cited by 3,261
Reducing Bias in Observational Studies Using Subclassification on the Propensity Score
Rosenbaum, P. R., & Rubin, D. B. (1984) · Journal of the American Statistical Association · doi:10.1080/01621459.1984.10478078 · Cited by 3,082 · cited 1×
“The first estimator relies on an initial estimate of the propensity score and uses subclassification (Rosenbaum and Rubin, 1983, 1984), combined with regression within the subclasses.”
MethodNonparametric Estimation of Average Treatment Effects Under Exogeneity: A Review
Imbens, G. W. (2004) · Review of Economics and Statistics · doi:10.1162/003465304323023651 · Cited by 2,994
Self-citationLarge sample properties of matching estimators for average treatment effects
Abadie, A., & Imbens, G. W. (2006) · Econometrica · doi:10.1111/j.1468-0262.2006.00655.x · Cited by 2,908
Self-citationEstimation of Average Treatment Effects Based on Propensity Scores
Becker, S. O., & Ichino, A. (2002) · The Stata Journal: Promoting communications on statistics and Stata · doi:10.1177/1536867x0200200403 · Cited by 2,754
Cited by
The State of Applied Econometrics: Causality and Policy Evaluation
Athey, S., & Imbens, G. W. (2017) · Journal of Economic Perspectives · doi:10.1257/jep.31.2.3 · Cited by 1,397
Self-citationRevisiting Event Study Designs
Borusyak, K., & Jaravel, X. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2826228 · Cited by 463
The Effects of the 1930s HOLC “Redlining” Maps
Aaronson, D., Hartley, D., & Mazumder, B. (2021) · American Economic Journal: Economic Policy · doi:10.1257/pol.20190414 · Cited by 349
“This approach is akin to the method of sub-classification, also known as blocking or stratification, discussed in Imbens (2015) and Imbens and Rubin (2015).”
MethodGordon, B. R., Zettelmeyer, F., Bhargava, N., & Chapsky, D. (2019) · Marketing Science · doi:10.1287/mksc.2018.1135 · Cited by 287
“A particularly flexible approach, advocated by Imbens (2015) and Eckles and Bakshy (2017), is to combine regression with stratification on the estimated propensity score.”
InfluentialShen, C.-H., Wu, M.-W., Chen, T.-H., & Fang, H. (2016) · Economic Modelling · doi:10.1016/j.econmod.2016.02.007 · Cited by 269
Aaronson, D., Faber, J., Hartley, D., Mazumder, B., & Sharkey, P. (2021) · Regional Science and Urban Economics · doi:10.1016/j.regsciurbeco.2020.103622 · Cited by 171
Koch, N., & Basse Mama, H. (2019) · Energy Economics · doi:10.1016/j.eneco.2019.04.018 · Cited by 148
The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables
Lakkaraju, H., Kleinberg, J., Leskovec, J., Ludwig, J., & Mullainathan, S. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098066 · Cited by 138
“(2) non-parametric methods such as propensity score matching, nearest-neighbor matching, which do not explicitly model the relationship between observed features, treatments, and outcomes [4, 15, 35, 36, 41].”
MethodYang, S., & Ding, P. (2018) · Biometrika · doi:10.1093/biomet/asy008 · Cited by 75
Mozart or Pelé? The effects of adolescents' participation in music and sports
Cabane, C., Hille, A., & Lechner, M. (2016) · Labour Economics · doi:10.1016/j.labeco.2016.05.012 · Cited by 51
Returning Home after Civil War: Food Security and Nutrition among Burundian Households
Verwimp, P., & Muñoz-Mora, J. C. (2018) · The Journal of Development Studies · doi:10.1080/00220388.2017.1311407 · Cited by 51
“Moreover, because of the lack of additional pretreatment variables, our adjustments through matching might fail to account for some relevant unmeasured covariant that simultaneously affects assignment to treatment and the outcome variable (Guido Imbens, 2015).”
BackgroundAn Examination of Early Transfers to the ICU Based on a Physiologic Risk Score
Hu, W., Chan, C. W., Zubizarreta, J. R., & Escobar, G. J. (2018) · Manufacturing & Service Operations Management · doi:10.1287/msom.2017.0658 · Cited by 44
“Another problem which can be missed when doing routine regression analysis is that, with pure modelbased adjustments, a few observations can unduly influence the results of a study (see Imbens (2015) and Rosenbaum (2016)).”
Migration and Housing Price Effects of Place-Based College Scholarships
Bartik, T. J., & Sotherland, N. (2015) · doi:10.17848/wp15-245 · Cited by 21
Harding, D., Sanbonmatsu, L., Duncan, G., Gennetian, L., Katz, L., Kessler, R., Kling, J., Sciandra, M., & Ludwig, J. (2021) · doi:10.3386/w28454 · Cited by 7
Metadata
- Authors
- Imbens, G. W.
- Venue
- Journal of Human Resources
- Publisher
- University of Wisconsin Press
- Published
- 2015
- Volume
- 50
- Issue
- 2
- Pages
- 373-419
- ISSN
- 0022-166X (ISSN-L)
- 1548-8004
- OpenAlex
- W2892053163
- Cited by
- 445
- References
- 51
- FWCI
- 30.37
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.