Abstract
Matching is used to control for imbalances between groups, but the preferable strategy
for matching is not always clear. We sought to compare two algorithms—optimal matching
with a fixed number of controls (OMFC), and optimal matching with a variable number
of controls (OMVC). We compared the degree of bias reduction and relative precision
using Monte Carlo simulations. We systematically changed the magnitude of the matching
variable difference, the variance ratios of the matching variable in the exposed and
unexposed groups, the sample size, and the number of unexposed subjects available
for matching. OMVC always produced larger removal of bias than the OMFC. The mean
percentage reduction of bias was 38.3 with the OMFC and 52.6 with OMVC. OMVC increased
the variance 6%. OMVC should be employed when researchers have access to a pool of
unexposed subjects because it removes more bias with little loss in precision.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Journal of Clinical EpidemiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Observational studies.in: Rosenbaum P.R. Observational studies. Springer-Verlag;, New York1995: 1-12
- Matching.in: Rothman K.J. Greenland S. Modern epidemiology. 2nd ed. Lippincott-Raven;, New York1998: 147-161
- Optimal case–control matching in practice.Epidemiology. 1994; 6: 271-275
- Optimal matching for observational studies.JASA. 1989; 84: 1024-1032
- A characterization of optimal designs for observational studies.J R Stat Soc Series B. 1988; 53: 597-610
- Applications of stratified analysis methods.in: Rothman K.J. Greenland S. Modern epidemiology. 2nd ed. Lippincott-Raven Publishers;, Philadelphia1998: 281-300
- Comparison of multivariate matching methods.J Comput Graph Stat. 1993; 2: 405-420
- Substantial gains in bias reduction from matching with a variable number of controls.Biometrics. 2000; 56: 118-124
- Introduction.in: Lewis-Beck M.S. Monte Carlo simulation. Sage Publications;, Thousands Oaks, CA1997: 3-4
- Efficiency of case control studies with multiple controls per case.Biometrics. 1975; 31: 643-649
- Matching using estimated propensity score.Biometrics. 1996; 52: 249-264
- Using multivariate matched sampling and regression adjustment to control bias in observational studies.JASA. 1979; 74: 318-328
- The use of matched sampling and regression adjustment to remove bias in observational studies.Biometrics. 1973; 29: 185-203
- Software for optimal matching in observational studies.Epidemiology. 1996; 7: 331-332
- Methods of sampling and estimation of sample size.in: Kelsey J.L. Whittemore A.S. Evans A.S. Thompson W.D. Methods in observational epidemiology. 2nd ed. Oxford University Press;, New York1996: 311-340
Bradley EL. Overlapping coefficient. In: Kotz S, Johnson NL, Read CB, editors. Encyclopedia of Statistical Sciences. New York: Wiley, 1985; Vol. 6, p. 546–47.
- Subgroup analysis and other (mis)uses of baseline data in clinical trials.Lancet. 2000; 355: 1064-1069
- The planning of observational studies of human populations.J R Stat Soc Series A. 1965; 128: 234-255
- Constructing a control group using multivariate matched sampling methods that incorporate the propensity score.Am Stat. 1985; 39: 33-38
- Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group.Stat Med. 1998; 17: 2265-2281
- The use of propensity score in pharmaco epidemiologic research.Pharmacoepidemiol Drug Saf. 2000; 9: 103-104
Article info
Publication history
Accepted:
November 4,
2002
Received in revised form:
July 25,
2002
Received:
May 30,
2001
Identification
Copyright
© 2003 Elsevier Science Inc. Published by Elsevier Inc. All rights reserved.
