The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Optimal multivariate matching before randomization
Abstract
Although blocking or pairing before randomization is a basic principle of experimental design, the principle is almost invariably applied to at most one or two blocking variables. Here, we discuss the use of optimal multivariate matching prior to randomization to improve covariate balance for many variables at the same time, presenting an algorithm and a case-study of its performance. The method is useful when all subjects, or large groups of subjects, are randomized at the same time. Optimal matching divides a single group of 2n subjects into n pairs to minimize covariate differences within pairs-the so-called nonbipartite matching problem-then one subject in each pair is picked at random for treatment, the other being assigned to control. Using the baseline covariate data for 132 patients from an actual, unmatched, randomized experiment, we construct 66 pairs matching for 14 covariates. We then create 10000 unmatched and 10000 matched randomized experiments by repeatedly randomizing the 132 patients, and compare the covariate balance with and without matching. By every measure, every one of the 14 covariates was substantially better balanced when randomization was performed within matched pairs. Even after covariance adjustment for chance imbalances in the 14 covariates, matched randomizations provided more accurate estimates than unmatched randomizations, the increase in accuracy being equivalent to, on average, a 7% increase in sample size. In randomization tests of no treatment effect, matched randomizations using the signed rank test had substantially higher power than unmatched randomizations using the rank sum test, even when only 2 of 14 covariates were relevant to a simulated response. Unmatched randomizations experienced rare disasters which were consistently avoided by matched randomizations.
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
Fisher, R. A. (1936) · BMJ · doi:10.1136/bmj.1.3923.554-a · Cited by 4,980
Pocock, S. J., & Simon, R. (1975) · Biometrics · doi:10.2307/2529712 · Cited by 2,350
The Effect of Myopia and Loss Aversion on Risk Taking: An Experimental Test
Thaler, R. H., Tversky, A., Kahneman, D., & Schwartz, A. (1997) · The Quarterly Journal of Economics · doi:10.1162/003355397555226 · Cited by 1,051
Comparison of Multivariate Matching Methods: Structures, Distances, and Algorithms
Gu, X. S., & Rosenbaum, P. R. (1993) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.1993.10474623 · Cited by 702
Self-citationRubin, D. B. (1979) · Journal of the American Statistical Association · doi:10.2307/2286330 · Cited by 341
Properties of permuted-block randomization in clinical trials
Matts, J. P., & Lachin, J. M. (1988) · Controlled Clinical Trials · doi:10.1016/0197-2456(88)90047-5 · Cited by 321
Cited by
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
Misunderstandings Between Experimentalists and Observationalists about Causal Inference
Imai, K., King, G., & Stuart, E. A. (2008) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/j.1467-985x.2007.00527.x · Cited by 906
In Pursuit of Balance: Randomization in Practice in Development Field Experiments
Bruhn, M., & McKenzie, D. (2009) · American Economic Journal: Applied Economics · doi:10.1257/app.1.4.200 · Cited by 788
Financial Incentives and Student Achievement: Evidence from Randomized Trials *
Fryer, R. G. (2011) · The Quarterly Journal of Economics · doi:10.1093/qje/qjr045 · Cited by 416
Rerandomization to improve covariate balance in experiments
Morgan, K. L., & Rubin, D. B. (2012) · The Annals of Statistics · doi:10.1214/12-aos1008 · Cited by 353
Best Practices in Quasi–Experimental Designs: Matching Methods for Causal Inference
Stuart, E. A., & Rubin, D. B. (2008) · Best Practices in Quantitative Methods · doi:10.4135/9781412995627.d14 · Cited by 335
In Pursuit Of Balance: Randomization In Practice In Development Field Experiments
McKenzie, D., & Bruhn, M. (2008) · World Bank, Washington, DC eBooks · doi:10.1596/1813-9450-4752 · Cited by 335
Fryer, R. G. (2014) · The Quarterly Journal of Economics · doi:10.1093/qje/qju011 · Cited by 295
Imai, K., King, G., & Nall, C. (2009) · Statistical Science · doi:10.1214/08-sts274 · Cited by 291
Gordon, B. R., Zettelmeyer, F., Bhargava, N., & Chapsky, D. (2019) · Marketing Science · doi:10.1287/mksc.2018.1135 · Cited by 287
Enhancing the Efficacy of Teacher Incentives through Loss Aversion: A Field Experiment
Fryer, R., Levitt, S., List, J., & Sadoff, S. (2012) · National Bureau of Economic Research · doi:10.3386/w18237 · Cited by 272
An Exact Distribution-Free Test Comparing Two Multivariate Distributions based on Adjacency
Rosenbaum, P. R. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00513.x · Cited by 255
Nelson, L. A., Greevy, R. A., Spieker, A., Wallston, K. A., Elasy, T. A., Kripalani, S., Gentry, C., Bergner, E. M., LeStourgeon, L. M., Williamson, S. E., et al. (2021) · Diabetes Care · doi:10.2337/dc20-0961 · Cited by 74
“1) to randomize participants (details in Supplementary Material) using optimal multivariate matching to ensure a covariate balance across study conditions (21).”
BackgroundSelf-citationOptimized design and analysis of preclinical intervention studies in vivo
Laajala, T. D., Jumppanen, M., Huhtaniemi, R., Fey, V., Kaur, A., Knuuttila, M., Aho, E., Oksala, R., Westermarck, J., Mäkelä, S., et al. (2016) · Scientific Reports · doi:10.1038/srep30723 · Cited by 48
Smith-Bindman, R., Chu, P., Wang, Y., Chung, R., Lopez-Solano, N., Einstein, A. J., Solberg, L., Cervantes, L. F., Nelson, T. R., Boswell, W., et al. (2020) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2020.0064 · Cited by 23
Sideman, A. B., Nguyen, H. Q., Langer-Gould, A., Lee, E. A., Borson, S., Shen, E., Tsoy, E., Macias, M., Goode, C., Rankin, K., et al. (2024) · BMC Primary Care · doi:10.1186/s12875-024-02544-9 · Cited by 4
“[20, 21] Matching variables included number of providers, median panel size, percentage of members self-identified as Black/African American, Hispanic/Latino or Asian/Pacific Islander, baseline rate of CI diagnoses, rates of telehealth encounters, and percentage of members who were 65 + in the…”
Background
Metadata
- Authors
- Greevy, R.
- Venue
- Biostatistics
- Publisher
- Oxford University Press (OUP)
- Published
- 2004-04-01
- Volume
- 5
- Issue
- 2
- Pages
- 263-275
- ISSN
- 1465-4644 (ISSN-L)
- 1468-4357
- OpenAlex
- W2102361189
- Cited by
- 205
- References
- 6
- FWCI
- 2.62
- Type
- journal article
- Language
- en
- Open access
- closed
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.