More on propensity score models (June 26, 2006).

Several months ago, I set out to develop some good examples of how to use propensity scores to adjust for covariate imbalance in an observational study. The original weblog entry was

• Stats: Propensity scores (March 10, 2006, Model, Linear regression)

followed by another entry:

• Stats: A simple application of propensity scores (April 26, 2006, Model, Linear regression)

I was consulting with someone recently about this very issue and she brought some additional references to my attention. I then dug a bit further and found some additional references as well.

Some good general references are

• Causal Effects in Clinical and Epidemiological Studies Via Potential Outcomes: Concepts and Analytical Approaches. Roderick J. Little, Donald B. Rubin. Annu. Rev Public Health 2000: 21; 121-145. [Medline] (Evidence, Apples, Observational, Establishing Causation)
• Estimation from nonrandomized treatment comparisons using subclassification on propensity scores. D. B. Rubin, Published in the Proceedings of the International Conference on Nonrandomized Comparative Clinical Studies in Heidelberg, April 10 -11,1997. . Accessed on 2005-01-12. (Evidence, Internal validity)
• Comparison of logistic regression versus propensity score when the number of events is low and there are multiple confounders. M. S. Cepeda, R. Boston, J. T. Farrar, B. L. Strom. Am J Epidemiol 2003: 158(3); 280-7. [Medline] [Abstract] [Full text] [PDF] (Model, Propensity score)
• Analytic strategies to adjust confounding using exposure propensity scores and disease risk scores: nonsteroidal antiinflammatory drugs and short-term mortality in the elderly. T. Sturmer, S. Schneeweiss, M. A. Brookhart, K. J. Rothman, J. Avorn, R. J. Glynn. Am J Epidemiol 2005: 161(9); 891-8. [Medline] [Abstract] [Full text] [PDF]
• Results of multivariable logistic regression, propensity matching, propensity adjustment, and propensity-based weighting under conditions of nonuniform effect. T. Kurth, A. M. Walker, R. J. Glynn, K. A. Chan, J. M. Gaziano, K. Berger, J. M. Robins. Am J Epidemiol 2006: 163(3); 262-70. [Medline] [Abstract]
• Using Propensity Scores to Adjust for Group Differences: Examples Comparing Alternative Surgical Methods [PDF]. David J. Pasta, published in the proceedings of the 25th annual Sas Users Group International meeting. Accessed on 2006-06-26. www2.sas.com/proceedings/sugi25/25/st/25p261.pdf

Three good published applications of the propensity score model are

• Surgical Revascularization Versus Amputation for Peripheral Vascular Disease in Dialysis Patients: A Cohort Study. C.M. Logar, L.M. Pappas, N. Ramkumar, S. Beddhu. BMC 2005: 6(1); 3. [Abstract] [Full text] [PDF] (Evidence, Corroboration, Strong association)
• Does prophylactic sotalol and magnesium decrease the incidence of atrial fibrillation following coronary artery bypass surgery: a propensity-matched analysis. V Aerra, M Kuduvalli, AN Moloto, AK Srinivasan, AD Grayson, BM Fabri, AY Oo. Journal of Cardiothoracic Surgery 2006: 1(6); [Abstract] [Full text] [PDF] (Model, Linear regression)
• Is albumin administration in the acutely ill associated with increased mortality? Results of the SOAP study. JL Vincent, Y Sakr, K Reinhart, CL Sprung, H Gerlach, VM Ranieri. Crit Care 2005: 9(6); R745-54. [Medline] [Abstract] [Full text] [PDF] (Model, Linear regression, Propensity score)

There is also an R library, USPS, that will compute propensity score models.

• cran.r-project.org/doc/packages/USPS.pdf

This page was written by Steve Simon while working at Children's Mercy Hospital. Although I do not hold the copyright for this material, I am reproducing it here as a service, as it is no longer available on the Children's Mercy Hospital website. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at Category: Covariate adjustment.