Variable Selection for Propensity Score Models
Open accessThe DOI matches its Crossref record; 21 of the 22 references it cites were found in a registry or an index.
Abstract
Despite the growing popularity of propensity score (PS) methods in epidemiology, relatively little has been written in the epidemiologic literature about the problem of variable selection for PS models. The authors present the results of two simulation studies designed to help epidemiologists gain insight into the variable selection problem in a PS analysis. The simulation studies illustrate how the choice of variables that are included in a PS model can affect the bias, variance, and mean squared error of an estimated exposure effect. The results suggest that variables that are unrelated to the exposure but related to the outcome should always be included in a PS model. The inclusion of these variables will decrease the variance of an estimated exposure effect without increasing bias. In contrast, including variables that are related to the exposure but not to the outcome will increase the variance of the estimated exposure effect without decreasing bias. In very small studies, the inclusion of variables that are strongly related to the exposure but only weakly related to the outcome can be detrimental to an estimate in a mean squared error sense. The addition of these variables removes only a small amount of bias but can increase the variance of the estimated exposure effect. These simulation studies and other analytical results suggest that standard model-building tools designed to create good predictive models of the exposure will not always lead to optimal PS models, particularly in small studies.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In this study, propensity scores were estimated by logistic regression on selected covariates to not only improve the exposure effect ' s accuracy but also to minimize confounding bias (Brookhart et al., 2006).”
From Midwifery continuity of care, breastfeeding and neonatal hyperbilirubinemia: A retrospective cohort study (2024) · cites this paper as Brookhart et al., 2006
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“We used directed acyclic graphs to identify factors that could be associated with both reading for pleasure and children's strengths and difficulties, or with children's strengths and difficulties only based on previous empirical research (Brookhart et al., 2006; Caliendo and Kopeinig, 2008; Rubin, 2001; Sauer and VanderWeele, 2013).”
From Longitudinal associations between reading for pleasure and child maladjustment: Results from a propensity score matching analysis (2020) · cites this paper as Brookhart et al., 2006
In the citing paper
“Preference was given to the variables believed to be related to the outcome of interest; thereby reducing the variance engendered due to the inclusion of variables which are unrelated to the outcome [48,58].”
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
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
R: A Language for Data Analysis and Graphics
Ihaka, R., & Gentleman, R. (1996) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.1996.10474713 · Cited by 11,220
Harrell, F. E. (2001) · Springer Series in Statistics · doi:10.1007/978-1-4757-3462-1 · Cited by 9,195
Marginal Structural Models and Causal Inference in Epidemiology
Robins, J. M., Hernán, M. Á., & Brumback, B. (2000) · Epidemiology · doi:10.1097/00001648-200009000-00011 · Cited by 5,581
Hastie, T., & Tibshirani, R. (2014) · Wiley StatsRef: Statistics Reference Online · doi:10.1002/9781118445112.stat03141 · Cited by 3,156
Estimating Causal Effects from Large Data Sets Using Propensity Scores
Rubin, D. B. (1997) · Annals of Internal Medicine · doi:10.7326/0003-4819-127-8_part_2-199710151-00064 · Cited by 2,877
Matching Using Estimated Propensity Scores: Relating Theory to Practice
Rubin, D. B., & Thomas, N. (1996) · Biometrics · doi:10.2307/2533160 · Cited by 1,074
Invited Commentary: Propensity Scores
Joffe, M. M., & Rosenbaum, P. R. (1999) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a010011 · Cited by 1,048
Hirano, K., & Imbens, G. W. (2001) · Health Services and Outcomes Research Methodology · doi:10.1023/a:1020371312283 · Cited by 1,039 · cited 1×
“Hirano and Imbens proposed a variable selection strategy for use with a multivariate outcome model employing propensity score weighting [6].”
MethodMatching Using Estimated Propensity Scores: Relating Theory to Practice
Thomas, N. (2006) · Matched Sampling for Causal Effects · doi:10.1017/cbo9780511810725.024 · Cited by 1,018
Rosenbaum, P. R. (1987) · Journal of the American Statistical Association · doi:10.1080/01621459.1987.10478441 · Cited by 997
Controlling Bias in Observational Studies: A Review
Cochran, W. G. (2006) · Matched Sampling for Causal Effects · doi:10.1017/cbo9780511810725.005 · Cited by 958
GAIL, M. H., WIEAND, S., & PIANTADOSI, S. (1984) · Biometrika · doi:10.1093/biomet/71.3.431 · Cited by 698
Stürmer, T., Joshi, M., Glynn, R. J., Avorn, J., Rothman, K. J., & Schneeweiss, S. (2006) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2005.07.004 · Cited by 670
Self-citationEstimating Exposure Effects by Modelling the Expectation of Exposure Conditional on Confounders
Robins, J. M., Mark, S. D., & Newey, W. K. (1992) · Biometrics · doi:10.2307/2532304 · Cited by 391
Principles for modeling propensity scores in medical research: a systematic literature review
Weitzen, S., Lapane, K. L., Toledano, A. Y., Hume, A. L., & Mor, V. (2004) · Pharmacoepidemiology and Drug Safety · doi:10.1002/pds.969 · Cited by 344
On principles for modeling propensity scores in medical research
Rubin, D. B. (2004) · Pharmacoepidemiology and Drug Safety · doi:10.1002/pds.968 · Cited by 287
van der Laan, M. J., & Dudoit, S. (2003) · Collection of Biostatistics Research Archive · Cited by 247
The use of propensity scores in pharmacoepidemiologic research
Perkins, S. M., Tu, W., Underhill, M. G., Zhou, X.-H., & Murray, M. D. (2000) · Pharmacoepidemiology and Drug Safety · doi:10.1002/(sici)1099-1557(200003/04)9:2<93::aid-pds474>3.0.co;2-i · Cited by 134
A semiparametric model selection criterion with applications to the marginal structural model
Brookhart, M. A., & van der Laan, M. J. (2004) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2004.08.013 · Cited by 47
Self-citationD’Agostino (1998) · doi:10.1002/(sici)1097-0258(19981015)17:19<2265::aid-sim918>3.0.co;2-b
Cited by
Austin, P. C. (2011) · Multivariate Behavioral Research · doi:10.1080/00273171.2011.568786 · Cited by 12,242
“…in this journal was written as a companion to this article to illustrate the application of propensity score methods to estimate the reduction in mortality due to provision of in-hospital smoking cessation counseling to current smokers who had been hospitalized with a heart attack (Austin, 2011a).”
BackgroundResultHainmueller, J. (2012) · Political Analysis · doi:10.1093/pan/mpr025 · Cited by 6,026
Matching Methods for Causal Inference: A Review and a Look Forward
Stuart, E. A. (2010) · Statistical Science · doi:10.1214/09-sts313 · Cited by 5,478
Why Propensity Scores Should Not Be Used for Matching
King, G., & Nielsen, R. (2019) · Political Analysis · doi:10.1017/pan.2019.11 · Cited by 1,706
Review of inverse probability weighting for dealing with missing data
Seaman, S. R., & White, I. R. (2013) · Statistical Methods in Medical Research · doi:10.1177/0962280210395740 · Cited by 1,654
Metadata
- Authors
- Brookhart, M. A., Schneeweiss, S., Rothman, K. J., Glynn, R. J., Avorn, J., & Stürmer, T.
- Affiliations
- Brigham and Women's Hospital (US)
- Boston University (US)
- Corresponding author
- Brookhart, M. Alan
- Venue
- American Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2006-04-19
- Volume
- 163
- Issue
- 12
- Pages
- 1149-1156
- ISSN
- 0002-9262 (ISSN-L)
- 1476-6256
- PMC
- PMC1513192
- OpenAlex
- W2168458505
- Cited by
- 2,336
- References
- 22
- Citations by year
- 2026: 142 · 2025: 165 · 2024: 184 · 2023: 161 · 2022: 210 · 2021: 205 · 2020: 193 · 2019: 173 · 2018: 125 · 2017: 133 · 2016: 111 · 2015: 90 · 2014: 104 · 2013: 80 · 2012: 76
- FWCI
- 27.83
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- American Journal of Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institute on Aging (AG023178, R01AG023178)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Keywords
- feature selection, propensity score models, exposure effect estimation, bias-variance trade-off, mean squared error, confounding adjustment, model development, small sample studies
- MeSH terms
- Epidemiologic Methods, Humans, Monte Carlo Method, Regression Analysis, Models, Statistical, Confounding Factors, Epidemiologic, Effect Modifier, Epidemiologic
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.