CoChat

Evaluating large-scale propensity score performance through real-world and synthetic data experiments

Open access
Tian, Yuxi, Schuemie, Martijn J, Suchard, Marc A · 2018 · International Journal of Epidemiology
Cited by 169

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

Background: Propensity score adjustment is a popular approach for confounding control in observational studies. Reliable frameworks are needed to determine relative propensity score performance in large-scale studies, and to establish optimal propensity score model selection methods. Methods: We detail a propensity score evaluation framework that includes synthetic and real-world data experiments. Our synthetic experimental design extends the 'plasmode' framework and simulates survival data under known effect sizes, and our real-world experiments use a set of negative control outcomes with presumed null effect sizes. In reproductions of two published cohort studies, we compare two propensity score estimation methods that contrast in their model selection approach: L1-regularized regression that conducts a penalized likelihood regression, and the 'high-dimensional propensity score' (hdPS) that employs a univariate covariate screen. We evaluate methods on a range of outcome-dependent and outcome-independent metrics. Results: L1-regularization propensity score methods achieve superior model fit, covariate balance and negative control bias reduction compared with the hdPS. Simulation results are mixed and fluctuate with simulation parameters, revealing a limitation of simulation under the proportional hazards framework. Including regularization with the hdPS reduces commonly reported non-convergence issues but has little effect on propensity score performance. Conclusions: L1-regularization incorporates all covariates simultaneously into the propensity score model and offers propensity score performance superior to the hdPS marginal screen.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/ije/dyy120

Cites

13 of 13 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 35

  1. Brookhart, 2010, Confounding control in healthcare database research: challenges and potential approaches, Med Care, 48, S114, 10.1097/MLR.0b013e3181dbebe3 · DOI · Paper page
  2. Ryan, 2012, Empirical assessment of methods for risk identification in healthcare data: results from the experiments of the Observational Medical Outcomes Partnership, Stat Med, 31, 4401, 10.1002/sim.5620 · DOI · Paper page
  3. Rubin, 1997, Estimating causal effects from large data sets using propensity scores, Ann Intern Med, 127, 757, 10.7326/0003-4819-127-8_Part_2-199710151-00064 · DOI · Paper page
  4. Rosenbaum, 1983, The central role of the propensity score in observational studies for causal effects, Biometrika, 70, 41, 10.1093/biomet/70.1.41 · DOI · Paper page
  5. Rubin, 1996, Matching using estimated propensity scores: relating theory to practice, Biometrics, 52, 249, 10.2307/2533160 · DOI · Paper page
  6. Franklin, 2017, Comparing the performance of propensity score methods in healthcare database studies with rare outcomes, Stat Med, 36, 1946
  7. Austin, 2013, The performance of different propensity score methods for estimating marginal hazard ratios, Stat Med, 32, 2837, 10.1002/sim.5705 · DOI · Paper page
  8. Schneeweiss, 2017, Variable selection for confounding adjustment in high-dimensional covariate spaces when analyzing healthcare databases, Epidemiology, 28, 237, 10.1097/EDE.0000000000000581 · DOI · Paper page
  9. Franklin, 2015, Regularized regression versus the high-dimensional propensity score for confounding adjustment in secondary database analyses, Am J Epidemiol, 182, 651, 10.1093/aje/kwv108 · DOI
  10. Rassen, 2011, Covariate selection in high-dimensional propensity score analyses of treatment effects in small samples, Am J Epidemiol, 173, 1404, 10.1093/aje/kwr001 · DOI · Paper page
  11. Imai, 2014, Covariate balancing propensity score, J R Stat Soc B, 76, 243, 10.1111/rssb.12027 · DOI · Paper page
  12. Shortreed, 2017, Outcome-adaptive lasso: variable selection for causal inference, Biometrics, 73, 1111, 10.1111/biom.12679 · DOI · Paper page
  13. Mansournia, 2018, Separation in logistic regression–causes, consequences, and control, Am J Epidemiol, 187, 864, 10.1093/aje/kwx299 · DOI · Paper page
  14. Tibshirani, 1996, Regression shrinkage and selection via the lasso, J R Stat Soc B, 57, 267, 10.1111/j.2517-6161.1996.tb02080.x · DOI · Paper page
  15. Ryan, 2013, Empirical performance of a new user cohort method: Lessons for developing a risk identification and analysis system, Drug Saf, 36, 59, 10.1007/s40264-013-0099-6 · DOI
  16. Greenland, 2007, Invited commentary: variable selection versus shrinkage in the control of multiple confounders, Am J Epidemiol, 167, 523, 10.1093/aje/kwm355 · DOI · Paper page
  17. Garbe, 2013, High-dimensional versus conventional propensity scores in a comparative effectiveness study of coxibs and reduced upper gastrointestinal complications, Eur J Clin Pharmacol, 69, 549, 10.1007/s00228-012-1334-2 · DOI
  18. Bender, 2005, Generating survival times to simulate Cox proportional hazards models, Stat Med, 24, 1713, 10.1002/sim.2059 · DOI · Paper page
  19. Franklin, 2014, Plasmode simulation for the evaluation of pharmacoepidemiologic methods in complex healthcare databases, Comput Stat Data Anal, 72, 219, 10.1016/j.csda.2013.10.018 · DOI
  20. Vaughan, 2009, The use of plasmodes as a supplement to simulations: A simple example evaluating individual admixture estimation methodologies, Comput Stat Data Anal, 53, 1755, 10.1016/j.csda.2008.02.032 · DOI
  21. Voss, 2017, Accuracy of an automated knowledge base for identifying drug adverse reactions, J Biomed Inform, 66, 72, 10.1016/j.jbi.2016.12.005 · DOI · Paper page
  22. Walker, 1991, Observation and Inference: An introduction to the Methods of Epidemiology
  23. Zhou, 2017, Sentinel modular program for propensity score–matched cohort analyses: application to glyburide, glipizide, and serious hypoglycemia, Epidemiology, 28, 838, 10.1097/EDE.0000000000000709 · DOI
  24. Suchard, 2013, Massive parallelization of serial inference algorithms for a complex generalized linear model, ACM Trans Model Comput Simul, 23, 1., 10.1145/2414416.2414791 · DOI · Paper page
  25. Schuemie, CohortMethod: New-User Cohort Method with Large Scale Propensity and Outcome Models
  26. Austin, 2008, Assessing balance in measured baseline covariates when using many-to-one matching on the propensity-score, Pharmacoepidemiol Drug Saf, 17, 1218, 10.1002/pds.1674 · DOI · Paper page
  27. Franklin, 2014, Metrics for covariate balance in cohort studies of causal effects, Stat Med, 33, 1685, 10.1002/sim.6058 · DOI · Paper page
  28. Gail, 1984, Biased estimates of treatment effect in randomized experiments with nonlinear regressions and omitted covariates, Biometrika, 71, 431, 10.1093/biomet/71.3.431 · DOI · Paper page
  29. Weitzen, 2005, Weaknesses of goodness-of-fit tests for evaluating propensity score models: The case of the omitted confounder, Pharmacoepidemiol Drug Saf, 14, 227, 10.1002/pds.986 · DOI · Paper page
  30. Austin, 2007, A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: a Monte Carlo study, Stat Med, 26, 734, 10.1002/sim.2580 · DOI · Paper page
  31. Westreich, 2011, The role of the c-statistic in variable selection for propensity score models, Pharmacoepidemiol Drug Saf, 20, 317, 10.1002/pds.2074 · DOI · Paper page
  32. Kumamaru, 2016, Comparison of high-dimensional confounder summary scores in comparative studies of newly marketed medications, J Clin Epidemiol, 76, 200, 10.1016/j.jclinepi.2016.02.011 · DOI
  33. Ding, 2017, Instrumental variables as bias amplifiers with general outcome and confounding, Biometrika, 104, 291, 10.1093/biomet/asx009 · DOI
  34. Westreich, 2010, Propensity score estimation: machine learning and classification methods as alternatives to logistic regression, J Clin Epidemiol, 63, 826., 10.1016/j.jclinepi.2009.11.020 · DOI · Paper page
  35. Greenland, 2015, Penalization, bias reduction, and default priors in logistic and related categorical and survival regressions, Stat Med, 34, 3133, 10.1002/sim.6537 · DOI · Paper page

Cited by

See all 169

Metadata

Authors
Tian, Y., Schuemie, M. J., & Suchard, M. A.
Venue
International Journal of Epidemiology
Published
2018-06-22
Volume
47
Issue
6
Pages
2005-2014
ISSN
  • 0300-5771 (ISSN-L)
  • 1464-3685
OpenAlex
W2808880546
Cited by
169
References
13
FWCI
10.88
Type
journal article
Language
en
Open access
bronze
Funders
  • National Science Foundation
  • Division of Information and Intelligent Systems (IIS 1251151)
  • National Institutes of Health
  • National Library of Medicine (1F31LM012636-01)
  • Paul and Daisy Soros Fellowships for New Americans

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.